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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 59711
    Prev
    Next
    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash

    Mentions of value-category and related terms (like rvalue/lvalue, temporary, expression, prvalue/xvalue) in C/C++ type/value discussions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    },{
    -0.07
     follower
    -0.07
    attery
    -0.07
     ViewState
    -0.07
     Dmitry
    -0.07
    .getMethod
    -0.07
     úč
    -0.07
     महत
    -0.06
     aute
    -0.06
     Gat
    -0.06
    POSITIVE LOGITS
     vaccination
    0.06
     sợ
    0.06
     rigged
    0.06
     poised
    0.06
     HeaderComponent
    0.06
    Ком
    0.06
     Д
    0.06
     renting
    0.06
    burse
    0.06
     installation
    0.06
    Activations Density 0.018%

    No Known Activations