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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124853
    Prev
    Next
    INDEX
    Explanations

    correspondence

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of company or organization names, especially when spelled out token by token as acronyms.

    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
     сад
    -0.07
    ň
    -0.06
    	bs
    -0.06
    mother
    -0.06
     invade
    -0.06
    arden
    -0.06
    _windows
    -0.06
     není
    -0.06
     surround
    -0.06
    Resolve
    -0.06
    POSITIVE LOGITS
     WARRANTIES
    0.07
    /F
    0.07
    \Core
    0.06
     SEC
    0.06
    /m
    0.06
    /
    0.06
     cleanly
    0.06
    ög
    0.06
    /c
    0.06
     jails
    0.06
    Activations Density 0.061%

    No Known Activations