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. 11-RESID-POST-AA
    6. 35699
    Prev
    Next
    INDEX
    Explanations

    case

    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
     label
    -0.07
     stamps
    -0.07
     Вели
    -0.07
    $client
    -0.07
    (display
    -0.07
     stamp
    -0.06
    ustos
    -0.06
    prefix
    -0.06
     mattress
    -0.06
     نیز
    -0.06
    POSITIVE LOGITS
     öngör
    0.06
     Fan
    0.06
     phenomen
    0.06
    て
    0.06
    ä
    0.06
    „A
    0.06
     northwest
    0.06
    ather
    0.06
    urls
    0.06
    万
    0.06
    Activations Density 0.003%

    No Known Activations