© 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. 68960
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects attribution phrases citing studies, surveys, reports, or sources (e.g., “according to a new study/survey/report…”).

    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
     diversion
    -0.07
    Menus
    -0.06
     політики
    -0.06
    uido
    -0.06
    edis
    -0.06
    delegate
    -0.06
    واز
    -0.06
    orts
    -0.06
    eced
    -0.06
    accent
    -0.06
    POSITIVE LOGITS
     este
    0.06
    _IL
    0.06
     aged
    0.06
    \Common
    0.06
     Collective
    0.06
    :before
    0.06
     dragging
    0.06
     passwd
    0.06
     n
    0.06
    _voice
    0.06
    Activations Density 0.022%

    No Known Activations