© 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. 126034
    Prev
    Next
    INDEX
    Explanations

    Gender

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of study participant demographics—numbers and labels indicating how many subjects (e.g. male, female, veterans) are included.

    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
    ूल
    -0.07
     د
    -0.07
     neob
    -0.06
    uC
    -0.06
     educators
    -0.06
    φυ
    -0.06
    ============↵
    -0.06
    .contract
    -0.06
    .books
    -0.06
    MYSQL
    -0.06
    POSITIVE LOGITS
    split
    0.06
    desired
    0.06
    asing
    0.06
    %E
    0.06
     elev
    0.06
     ►
    0.06
     окруж
    0.06
     viable
    0.06
    본
    0.06
    vocab
    0.05
    Activations Density 0.037%

    No Known Activations