© 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. 63397
    Prev
    Next
    INDEX
    Explanations

    code analysis/calculation

    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
    ικο
    -0.07
    ποιη
    -0.06
    كيل
    -0.06
    _SECURE
    -0.06
    ’na
    -0.06
    ném
    -0.06
    gın
    -0.06
    주시
    -0.06
    死亡
    -0.06
    ерап
    -0.06
    POSITIVE LOGITS
    _Pr
    0.07
    .internal
    0.07
    _PK
    0.06
    .Resize
    0.06
     Bomb
    0.06
    _phys
    0.06
    _D
    0.06
     conseils
    0.06
    .join
    0.06
    ivi
    0.06
    Activations Density 0.635%

    No Known Activations