Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 128947
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric tokens—especially dates, years, and other number‐formatted expressions.

    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
     fry
    -0.06
    -available
    -0.06
     amused
    -0.06
     repeating
    -0.06
     wrongdoing
    -0.06
     replication
    -0.06
     Fred
    -0.06
    xic
    -0.06
     advertise
    -0.06
    日の
    -0.06
    POSITIVE LOGITS
    ,,,,,,,,
    0.06
    .mvp
    0.06
    zh
    0.06
    ्रस
    0.06
     politik
    0.06
    Ã
    0.06
    uilder
    0.06
     Crushers
    0.06
    beiter
    0.06
    卡
    0.06
    Activations Density 0.016%

    No Known Activations