© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73743
    Prev
    Next
    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing precise measured or statistical values (e.g. decimal numbers like p-values or test statistics).

    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
     Rogue
    -0.06
    elize
    -0.06
    widgets
    -0.06
    Yellow
    -0.06
    ReadWrite
    -0.06
    razy
    -0.06
     Fus
    -0.06
     SON
    -0.06
     buzzing
    -0.06
    õi
    -0.06
    POSITIVE LOGITS
     قر
    0.06
    .exchange
    0.06
    /bash
    0.06
    ुआत
    0.06
    .micro
    0.06
     estas
    0.06
    earch
    0.06
    \v
    0.06
    .Assembly
    0.06
     kannst
    0.06
    Activations Density 0.073%

    No Known Activations