© 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. 13162
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates on key topic words (e.g. “basics,” “spices,” “equipment,” “braising”) that label or summarize individual steps in cooking instructions.

    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
    Danger
    -0.07
     institutional
    -0.07
    -param
    -0.06
    FixedSize
    -0.06
    Jer
    -0.06
     Alam
    -0.06
    _seconds
    -0.06
     telegram
    -0.06
    典
    -0.06
    _ids
    -0.06
    POSITIVE LOGITS
    ABL
    0.07
    .ImageField
    0.06
     Grocery
    0.06
     willen
    0.06
     [.
    0.06
     happier
    0.06
     ciddi
    0.06
     cinsel
    0.06
    .Address
    0.06
     detain
    0.06
    Activations Density 0.192%

    No Known Activations