© 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
    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. 30607
    Prev
    Next
    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash

    This neuron detects temporal anniversary or elapsed‐time expressions (e.g. “one year ago today,” “three months ago today,” “a year after…”).

    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
    request
    -0.07
    .guid
    -0.07
     مثال
    -0.06
     Teresa
    -0.06
    وپ
    -0.06
     MESSAGE
    -0.06
     princess
    -0.06
     SUN
    -0.06
     silly
    -0.06
    ندان
    -0.06
    POSITIVE LOGITS
     quizzes
    0.07
    tees
    0.06
    fid
    0.06
    Would
    0.06
    .Bool
    0.06
    acionales
    0.06
    volution
    0.06
     Kew
    0.06
     AB
    0.06
    .Gr
    0.06
    Activations Density 0.017%

    No Known Activations