© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 20914
    Prev
    Next
    INDEX
    Explanations

    wrestling

    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
     audits
    -0.07
     dying
    -0.07
     oo
    -0.07
    _Long
    -0.06
    Cit
    -0.06
     shade
    -0.06
    Beat
    -0.06
    Ctx
    -0.06
    _four
    -0.06
    aka
    -0.06
    POSITIVE LOGITS
     wrestling
    0.16
     Wrestling
    0.12
     wrestlers
    0.12
     wrest
    0.12
     wrestler
    0.10
     Wrestle
    0.09
     Wrest
    0.08
    .assertEqual
    0.07
    ",↵↵
    0.07
     Russell
    0.07
    Activations Density 0.003%

    No Known Activations