© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68671
    Prev
    Next
    INDEX
    Explanations

    starting

    np_max-act · gemini-2.0-flash

    The neuron fires on words marking the beginning or first‐unit of something—especially “starting” (and related forms like “start” or “opening”) in contexts such as game lineups or events.

    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
     unto
    -0.07
    popup
    -0.07
     fug
    -0.06
     priests
    -0.06
     bore
    -0.06
    movie
    -0.06
     영향
    -0.06
     MatButtonModule
    -0.06
    BALL
    -0.06
     така
    -0.06
    POSITIVE LOGITS
    /application
    0.07
    서는
    0.06
    !_
    0.06
     starters
    0.06
    ;"
    0.06
    RequestBody
    0.06
     ห
    0.06
     olduğ
    0.06
    |\
    0.06
    甲
    0.06
    Activations Density 0.005%

    No Known Activations