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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 124577
    Prev
    Next
    INDEX
    Explanations

    societal issues

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WA
    -0.07
    _PA
    -0.06
     Johann
    -0.06
     farmer
    -0.06
     Hayward
    -0.06
     peut
    -0.06
     Urdu
    -0.06
     inward
    -0.06
    Finish
    -0.06
    (Program
    -0.06
    POSITIVE LOGITS
    صة
    0.08
     ");
↵
    0.07
     />);↵
    0.07
    .identifier
    0.07
    .FindElement
    0.07
     같습니다
    0.07
    :{
↵
    0.06
     出
    0.06
     ")"
    0.06
     addSubview
    0.06
    Activations Density 0.298%

    No Known Activations