© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30530
    Prev
    Next
    INDEX
    Explanations

    section markers

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric and decimal tokens (e.g. section markers and floating‐point numbers).

    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
    ehicles
    -0.06
    §ط
    -0.06
    binary
    -0.06
    _DR
    -0.06
    ipherals
    -0.06
    assic
    -0.06
     riêng
    -0.06
    .getRequest
    -0.06
    Endpoints
    -0.06
     tým
    -0.06
    POSITIVE LOGITS
    (Text
    0.08
    _nth
    0.07
     الكتاب
    0.07
     mở
    0.06
    ?”
    0.06
    /load
    0.06
     Aqua
    0.06
     Jub
    0.06
     biting
    0.06
    จ
    0.06
    Activations Density 0.005%

    No Known Activations