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. 88648
    Prev
    Next
    INDEX
    Explanations

    Short news-like texts

    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
     gsi
    -0.06
    ocode
    -0.06
    了一
    -0.06
     ↵	↵
    -0.06
    guard
    -0.06
    ικών
    -0.06
    lightbox
    -0.06
    eč
    -0.06
    ına
    -0.06
    işti
    -0.06
    POSITIVE LOGITS
     вигля
    0.07
    WindowSize
    0.07
    extent
    0.06
    .");
    0.06
     Chiefs
    0.06
    arence
    0.06
    μα
    0.06
    >';
    ↵
    0.06
     elast
    0.06
    Compression
    0.06
    Activations Density 0.151%

    No Known Activations