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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 104427
    Prev
    Next
    INDEX
    Explanations

    line

    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
    anj
    -0.06
     jeopard
    -0.06
    ,last
    -0.06
    われた
    -0.06
     Basel
    -0.06
    aul
    -0.05
     Yam
    -0.05
    :flutter
    -0.05
    O
    -0.05
    AUD
    -0.05
    POSITIVE LOGITS
     ответ
    0.08
    .public
    0.08
    κυ
    0.07
    치
    0.07
    宽
    0.07
     виробництва
    0.07
    TIME
    0.07
     finely
    0.06
    ……
    0.06
     grief
    0.06
    Activations Density 0.001%

    No Known Activations