© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89742
    Prev
    Next
    INDEX
    Explanations

    Legal citations

    np_max-act · gemini-2.0-flash

    This neuron fires on numbers that are part of legal citation references (e.g. volume and page numbers).

    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
    .Est
    -0.07
     billed
    -0.07
     Kuala
    -0.06
    =>
    -0.06
    万元
    -0.06
     XMLHttpRequest
    -0.06
    500
    -0.06
    .Size
    -0.06
    	Color
    -0.06
     Mature
    -0.06
    POSITIVE LOGITS
    din
    0.07
     Cute
    0.07
     Piet
    0.07
    ندگی
    0.07
     kork
    0.06
    (Graph
    0.06
    ưu
    0.06
    ,it
    0.06
    bast
    0.06
    ğında
    0.06
    Activations Density 0.003%

    No Known Activations