Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130298
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron is detecting underscore characters in identifier names (e.g. C/C++ member or variable names that include a “_”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    ẽ
    -0.07
    JM
    -0.07
    PACK
    -0.06
     viz
    -0.06
     tímto
    -0.06
    CELER
    -0.06
    .methods
    -0.06
    Paris
    -0.06
     Bunlar
    -0.06
    ?>↵
    -0.06
    POSITIVE LOGITS
     Welsh
    0.07
    能
    0.06
     能
    0.06
    teş
    0.06
     Smith
    0.06
    lli
    0.06
    _sw
    0.06
     Spieler
    0.06
    >>(
    0.06
     cer
    0.06
    Activations Density 0.005%

    No Known Activations