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. 123008
    Prev
    Next
    INDEX
    Explanations

    current/present

    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
     Har
    -0.07
    猜
    -0.07
     fantasy
    -0.07
    arc
    -0.06
     Analy
    -0.06
     scarce
    -0.06
     facto
    -0.06
    الث
    -0.06
     Replace
    -0.06
    ingredients
    -0.06
    POSITIVE LOGITS
    .JButton
    0.07
    (directory
    0.06
    .getColor
    0.06
    oriasis
    0.06
    .setLayout
    0.06
     pizza
    0.06
    $ret
    0.06
    ../../../../
    0.06
    他們
    0.06
    .↵↵↵↵↵
    0.06
    Activations Density 0.019%

    No Known Activations