© 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. 94245
    Prev
    Next
    INDEX
    Explanations

    butter and/or butterfly

    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
    makt
    -0.07
     организации
    -0.07
     rank
    -0.07
     ocas
    -0.07
     phim
    -0.07
     FPS
    -0.06
     avanz
    -0.06
     Fonts
    -0.06
     NPC
    -0.06
     shards
    -0.06
    POSITIVE LOGITS
     Butter
    0.14
     butter
    0.14
    .Butter
    0.08
     FILTER
    0.07
    _strings
    0.07
     worrying
    0.06
     Burton
    0.06
    utter
    0.06
     cottage
    0.06
    .toast
    0.06
    Activations Density 0.002%

    No Known Activations