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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7951
    Prev
    Next
    INDEX
    Explanations

    separating titles or dates

    np_max-act · gemini-2.0-flash

    lists of award-winning films and their corresponding categories.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron strongly activates on television network or channel abbreviations (e.g. ABC, CBS, PBS, NBC, SYN).

    oai_token-act-pair · o4-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
     ingestion
    -0.07
     Azerbaijan
    -0.07
    	On
    -0.06
     sanki
    -0.06
    _rg
    -0.06
    .ContentType
    -0.06
     Crom
    -0.06
     Voll
    -0.06
    ewidth
    -0.06
     RedirectTo
    -0.06
    POSITIVE LOGITS
     (:
    0.07
     Mentor
    0.07
    성이
    0.06
    ListComponent
    0.06
     literary
    0.06
    ellery
    0.06
     Activate
    0.06
    ademic
    0.06
     temporarily
    0.06
    getName
    0.06
    Activations Density 0.007%

    No Known Activations