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. 80735
    Prev
    Next
    INDEX
    Explanations

    Code and configuration

    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
     الج
    -0.07
     nhắc
    -0.07
     molecular
    -0.07
     Wolff
    -0.07
    acist
    -0.06
     cursos
    -0.06
    EDIUM
    -0.06
    能力
    -0.06
    してる
    -0.06
    지막
    -0.06
    POSITIVE LOGITS
    .Exists
    0.06
     fig
    0.06
     ثبت
    0.06
     json
    0.06
    154
    0.06
    quires
    0.06
     Validator
    0.06
     endowed
    0.06
    Attrs
    0.05
    UpInside
    0.05
    Activations Density 0.004%

    No Known Activations