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. 85903
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point number literals (decimal values) in code.

    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
    bur
    -0.08
    AYS
    -0.07
    ulado
    -0.07
     processor
    -0.07
    кості
    -0.07
    RowCount
    -0.07
     mph
    -0.07
    ays
    -0.06
    -girl
    -0.06
    tones
    -0.06
    POSITIVE LOGITS
    (UnmanagedType
    0.07
     square
    0.06
    民
    0.06
    _COMMIT
    0.06
     Nhà
    0.06
    -'.$
    0.06
     useCallback
    0.06
     Fransız
    0.06
    ').'</
    0.06
    %M
    0.06
    Activations Density 0.096%

    No Known Activations