© 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. 42618
    Prev
    Next
    INDEX
    Explanations

    Code licenses

    np_max-act · gemini-2.0-flash

    This neuron detects formal license‐definition terms (e.g. “Covered Code,” “Modifications,” “Contributor,” “Original Code”) in software license headers.

    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
     storefront
    -0.06
    ेह
    -0.06
    setIcon
    -0.06
    (sb
    -0.06
     release
    -0.06
     nab
    -0.06
    Student
    -0.06
     fontWeight
    -0.06
     Madonna
    -0.06
    زار
    -0.06
    POSITIVE LOGITS
    /not
    0.07
     consideration
    0.07
     Japon
    0.07
     RTL
    0.06
     Prices
    0.06
    timing
    0.06
     retali
    0.06
    直播
    0.06
     cache
    0.06
    cleanup
    0.06
    Activations Density 0.010%

    No Known Activations