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. 23-RESID-POST-AA
    6. 103845
    Prev
    Next
    INDEX
    Explanations

    B

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conexión
    -0.06
    Wrap
    -0.06
    .day
    -0.06
     взаим
    -0.06
     فرو
    -0.06
     timeframe
    -0.06
     llen
    -0.06
     mommy
    -0.06
    Hub
    -0.06
     뿐
    -0.05
    POSITIVE LOGITS
    iyat
    0.08
     XO
    0.08
    stringLiteral
    0.07
    yle
    0.07
    иту
    0.07
    prak
    0.07
    арт
    0.07
    stration
    0.06
    -party
    0.06
    UIAlert
    0.06
    Activations Density 0.006%

    No Known Activations