© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43411
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron activates strongly on numeric tokens—especially digits, decimal numbers, and number ranges (e.g., "10-20", "0.304", "45-60").

    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
     Believe
    -0.08
     LOGIN
    -0.07
     ワ
    -0.07
    casts
    -0.07
    umsuz
    -0.07
     Thanks
    -0.06
    emento
    -0.06
    Wrap
    -0.06
     heap
    -0.06
     Harvey
    -0.06
    POSITIVE LOGITS
    afb
    0.08
    oomla
    0.07
    /logs
    0.07
     इसल
    0.06
    छ
    0.06
     Рез
    0.06
                ↵↵
    0.06
    �
    0.06
    ιθ
    0.06
    .Sql
    0.06
    Activations Density 0.021%

    No Known Activations