© 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. 110166
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that appear in C function or macro declarations—particularly the return‐type identifiers, pointer “*” symbols, and parameter names inside parentheses.

    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
     emergency
    -0.06
     queries
    -0.06
    řez
    -0.06
     імені
    -0.06
     dough
    -0.06
    _BINARY
    -0.06
     Hath
    -0.06
     huge
    -0.06
    _qos
    -0.06
     gigantic
    -0.06
    POSITIVE LOGITS
     (%)
    0.08
    stry
    0.07
     распростран
    0.07
    PCS
    0.06
     playground
    0.06
    \":\"
    0.06
     Playground
    0.06
    ^{
    0.06
    .ss
    0.06
    ür
    0.06
    Activations Density 0.005%

    No Known Activations