© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 97420
    Prev
    Next
    INDEX
    Explanations

    Hockey defenseman

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    typeid
    -0.07
    ListView
    -0.07
    .authService
    -0.06
     touchdowns
    -0.06
    ('#
    -0.06
     bindActionCreators
    -0.06
    _PUSHDATA
    -0.06
    ↵   ↵
    -0.06
    -Jan
    -0.06
    .ham
    -0.06
    POSITIVE LOGITS
    Local
    0.07
     locator
    0.06
     psych
    0.06
     ưu
    0.06
     learn
    0.06
     Played
    0.06
     mund
    0.06
    473
    0.06
    ASON
    0.06
    682
    0.06
    Activations Density 0.018%

    No Known Activations