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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 127796
    Prev
    Next
    INDEX
    Explanations

    computer-related/technical

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ている
    -0.08
    adal
    -0.07
    れている
    -0.07
    marvin
    -0.06
    look
    -0.06
     também
    -0.06
    _packages
    -0.06
    .abspath
    -0.06
    研
    -0.06
    ком
    -0.06
    POSITIVE LOGITS
    太郎
    0.07
     genç
    0.07
     변화
    0.06
    .va
    0.06
    symbol
    0.06
    BK
    0.06
     cał
    0.06
    .bunifuFlatButton
    0.06
     الكتاب
    0.06
     DMA
    0.06
    Activations Density 0.000%

    No Known Activations