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. 11-RESID-POST-AA
    6. 80708
    Prev
    Next
    INDEX
    Explanations

    the

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -nine
    -0.07
    -government
    -0.07
    linux
    -0.07
     careful
    -0.07
    寄
    -0.06
    abor
    -0.06
    Keywords
    -0.06
     incapable
    -0.06
     militants
    -0.06
     railways
    -0.06
    POSITIVE LOGITS
     UA
    0.07
    อกจาก
    0.06
    !<
    0.06
     decentral
    0.06
     pra
    0.06
    >V
    0.06
    ่อต
    0.06
     Кри
    0.06
    _Reg
    0.06
     Agile
    0.06
    Activations Density 0.101%

    No Known Activations