© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 39807
    Prev
    Next
    INDEX
    Explanations

    its

    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
     //--------------------------------
    -0.07
     Litecoin
    -0.07
    jectories
    -0.06
     ngăn
    -0.06
     Johann
    -0.06
     thịt
    -0.06
    (dAtA
    -0.06
    atıcı
    -0.06
    aticon
    -0.06
    leftrightarrow
    -0.06
    POSITIVE LOGITS
     Tomorrow
    0.06
     certified
    0.06
    require
    0.06
    wm
    0.06
    final
    0.06
     telescope
    0.06
     stripe
    0.06
     Injury
    0.06
     amused
    0.06
    heet
    0.06
    Activations Density 0.000%

    No Known Activations