© 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. 91917
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, especially years and date-like numbers.

    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
     Investigation
    -0.07
    .Call
    -0.07
    -process
    -0.07
     поли
    -0.07
     battalion
    -0.06
     protecting
    -0.06
    stroke
    -0.06
     vulgar
    -0.06
    ochastic
    -0.06
     Accident
    -0.06
    POSITIVE LOGITS
    erializer
    0.07
    σσα
    0.07
    ฏ
    0.07
    hyper
    0.07
     Baum
    0.07
    vector
    0.06
     männ
    0.06
     tin
    0.06
     الجم
    0.06
     cam
    0.06
    Activations Density 0.022%

    No Known Activations