© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57852
    Prev
    Next
    INDEX
    Explanations

    offers

    np_max-act · gemini-2.0-flash

    phrases and sentences indicating collaboration or partnership agreements between companies.

    oai_token-act-pair · gpt-4oTriggered by @tcai

    The neuron fires on promotional or evaluative adjectives that describe product or service features in marketing copy.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information about vehicle model announcements and specifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tome
    -0.07
    "There
    -0.06
     Meer
    -0.06
     Gott
    -0.06
     Barnes
    -0.06
     Uz
    -0.06
     Verg
    -0.06
    “There
    -0.06
     کد
    -0.06
    ImagePath
    -0.06
    POSITIVE LOGITS
    stants
    0.06
    	connect
    0.06
        
    0.06
     stdout
    0.06
    -ending
    0.06
    osit
    0.06
    Submitted
    0.06
    startdate
    0.06
     bewild
    0.06
    icies
    0.06
    Activations Density 0.102%

    No Known Activations