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. 30711
    Prev
    Next
    INDEX
    Explanations

    newborn

    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
    Degree
    -0.07
    629
    -0.06
    OUT
    -0.06
    输入
    -0.06
     naz
    -0.06
    xes
    -0.06
     ub
    -0.06
    ़ो
    -0.06
     المغرب
    -0.06
    لل
    -0.06
    POSITIVE LOGITS
    beans
    0.06
     플레이
    0.06
    $current
    0.06
     Gupta
    0.06
     scenarios
    0.06
    waitFor
    0.06
     functioning
    0.06
    (coeffs
    0.06
    .routes
    0.06
     Deposit
    0.06
    Activations Density 0.000%

    No Known Activations