© 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. 27-RESID-POST-AA
    11. 37058
    Prev
    Next
    INDEX
    Explanations

    Animals and eating habits

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yang
    -0.07
     peny
    -0.07
     assurances
    -0.06
    scal
    -0.06
    �情
    -0.06
     admits
    -0.06
     Photon
    -0.06
     ostensibly
    -0.06
    _PAIR
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
     cùng
    0.07
    епти
    0.07
    보고
    0.07
    unidad
    0.06
     zu
    0.06
     olmayan
    0.06
     použit
    0.06
     craz
    0.06
     보고
    0.06
     Phill
    0.06
    Activations Density 0.056%

    No Known Activations