© 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. 30158
    Prev
    Next
    INDEX
    Explanations

    Period tokens

    np_max-act · gemini-2.0-flash

    This neuron detects legal-document metadata elements such as docket numbers, case citations (e.g. “No.”, “D.C.”), and dates in the opinion header.

    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
    라
    -0.07
    ρες
    -0.07
     getSession
    -0.06
    Reuters
    -0.06
    _paint
    -0.06
     cauliflower
    -0.06
    classifier
    -0.06
    Don
    -0.06
    ospace
    -0.06
     brush
    -0.06
    POSITIVE LOGITS
     yüzden
    0.07
     cliente
    0.06
     prospective
    0.06
     RETURNS
    0.06
     Орг
    0.06
    시간
    0.06
    ']));
    0.06
    Maximum
    0.06
     церков
    0.06
    CALE
    0.06
    Activations Density 0.003%

    No Known Activations