Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 111297
    Prev
    Next
    INDEX
    Explanations

    Parenthesis

    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
     характериз
    -0.07
     Movie
    -0.07
    дивиду
    -0.07
     movie
    -0.07
     hamburger
    -0.07
    gf
    -0.06
    risk
    -0.06
    ülebilir
    -0.06
    .....↵↵
    -0.06
     Tape
    -0.06
    POSITIVE LOGITS
     ア
    0.06
     默认
    0.06
    onu
    0.06
    /twitter
    0.06
     qualify
    0.06
     ||
    0.06
     是否
    0.05
    。不过
    0.05
    лаб
    0.05
    .subplots
    0.05
    Activations Density 0.014%

    No Known Activations