© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85735
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron strongly responds to numbered list markers (e.g. “1.”, “2.”, etc.) used when the assistant is asking a series of questions or giving a numbered outline.

    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
    .toFloat
    -0.07
    _Float
    -0.07
    っ�
    -0.07
    .promise
    -0.07
    _COLS
    -0.06
     Hearth
    -0.06
    .getWidth
    -0.06
    익
    -0.06
    *f
    -0.06
    ppard
    -0.06
    POSITIVE LOGITS
    arris
    0.06
     Concurrent
    0.06
    .gwt
    0.06
    Dem
    0.06
     shown
    0.06
     شناس
    0.06
     Sail
    0.06
     decl
    0.06
    .json
    0.06
    елефон
    0.06
    Activations Density 0.057%

    No Known Activations