© 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. 85679
    Prev
    Next
    INDEX
    Explanations

    function arguments/parameters

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of functions being treated as first-class values—especially passing or assigning functions (including lambdas) as arguments or handlers.

    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
     neu
    -0.06
     bott
    -0.06
    744
    -0.06
    _AT
    -0.06
    dfa
    -0.06
     cessation
    -0.06
     WEIGHT
    -0.05
    แลนด
    -0.05
    Mer
    -0.05
    _padding
    -0.05
    POSITIVE LOGITS
    arhus
    0.07
    ocurrency
    0.07
     спис
    0.07
    romosome
    0.07
    點
    0.07
     Uni
    0.07
     surreal
    0.07
    panic
    0.06
     rejuven
    0.06
    .Suppress
    0.06
    Activations Density 0.020%

    No Known Activations