© 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. 60027
    Prev
    Next
    INDEX
    Explanations

    Cell-material interactions

    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
     Kou
    -0.07
    sep
    -0.07
     κα
    -0.07
     linkage
    -0.06
    _All
    -0.06
    _Pre
    -0.06
    Protection
    -0.06
     ensuing
    -0.06
     performances
    -0.06
     XmlDocument
    -0.06
    POSITIVE LOGITS
     disables
    0.07
    apyrus
    0.06
     Toro
    0.06
    bury
    0.06
     @"↵
    0.06
    яж
    0.06
    수로
    0.06
    [sizeof
    0.06
     fucks
    0.06
     Copyright
    0.06
    Activations Density 0.062%

    No Known Activations