© 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. 92612
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and does not detect any specific pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    This neuron detects text produced by the assistant (assistant-role replies).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    ey
    -0.06
    -flash
    -0.06
    30
    -0.06
     Tree
    -0.06
    otec
    -0.06
     Liqu
    -0.06
     zprávy
    -0.06
    atan
    -0.06
    퓨터
    -0.06
    Converter
    -0.06
    POSITIVE LOGITS
     hosting
    0.07
    >
    ↵
    ↵
    ↵
    0.07
    .paper
    0.06
    ernity
    0.06
    plays
    0.06
    ";
    ↵
    ↵
    0.06
    ':"
    0.06
     sidel
    0.06
     له
    0.06
     you
    0.06
    Activations Density 0.061%

    No Known Activations