© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 113252
    Prev
    Next
    INDEX
    Explanations

    C

    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
     annoying
    -0.07
    _bank
    -0.06
     Quadr
    -0.06
     long
    -0.06
    /bind
    -0.06
    _frame
    -0.06
     elucid
    -0.06
    interp
    -0.06
     logarith
    -0.06
    567
    -0.06
    POSITIVE LOGITS
     EditorGUI
    0.07
     cc
    0.07
     Found
    0.07
    _fk
    0.07
    .G
    0.06
     默认
    0.06
    (Editor
    0.06
    AutoresizingMask
    0.06
    .levels
    0.06
     »,
    0.06
    Activations Density 0.006%

    No Known Activations