© 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. 126238
    Prev
    Next
    INDEX
    Explanations

    conversational

    np_max-act · gemini-2.0-flash

    The neuron fires on the assistant’s lead-in tokens that introduce a step-by-step instruction or explanatory list (e.g. words like “Absolutely,” “Here,” the “A” of “A rebuttal is…,” and the colon that launches the numbered steps).

    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
    Including
    -0.08
     oldest
    -0.07
    (fragment
    -0.06
     Medi
    -0.06
     является
    -0.06
    盗
    -0.06
    /auth
    -0.06
    expired
    -0.06
    三个
    -0.06
    .camel
    -0.06
    POSITIVE LOGITS
    development
    0.07
     Responsive
    0.07
     makeStyles
    0.07
    stial
    0.07
     Mosul
    0.06
     commencement
    0.06
     Syria
    0.06
    _ur
    0.06
    []>
    0.06
    Architecture
    0.06
    Activations Density 0.236%

    No Known Activations