© 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. 7-RESID-POST-AA
    11. 36254
    Prev
    Next
    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     힘
    -0.07
    swana
    -0.07
     oby
    -0.07
    actice
    -0.07
     reaching
    -0.07
     Eig
    -0.07
    森
    -0.07
     sollte
    -0.06
    editar
    -0.06
    翼
    -0.06
    POSITIVE LOGITS
     thereby
    0.07
    mits
    0.07
    .cross
    0.06
    instant
    0.06
    .intersection
    0.06
     allocating
    0.06
    _dims
    0.06
    ographical
    0.06
    depart
    0.06
     Msg
    0.06
    Activations Density 0.001%

    No Known Activations