© 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. 23-RESID-POST-AA
    11. 63584
    Prev
    Next
    INDEX
    Explanations

    providing oversight/governance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contr
    -0.08
     uděl
    -0.07
    ']='
    -0.07
    िध
    -0.07
    outline
    -0.07
     Assembly
    -0.06
     assembly
    -0.06
    /(?
    -0.06
     pw
    -0.06
    -wide
    -0.06
    POSITIVE LOGITS
    .Result
    0.07
     takové
    0.06
    100
    0.06
     této
    0.06
    Answer
    0.06
    .Message
    0.05
    Scaled
    0.05
     مجموع
    0.05
     회원
    0.05
     詳細
    0.05
    Activations Density 0.036%

    No Known Activations