© 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. 30565
    Prev
    Next
    INDEX
    Explanations

    statistics and numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical expressions—counts, percentages, and other statistical figures—in the text.

    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
    ocular
    -0.06
    Bond
    -0.06
    ителем
    -0.06
     设
    -0.06
    手
    -0.06
    renal
    -0.06
    Arg
    -0.06
    Ranked
    -0.06
    併
    -0.06
     boxed
    -0.06
    POSITIVE LOGITS
    이었다
    0.08
     tyto
    0.07
    /gpl
    0.06
    >';↵↵
    0.06
    =$((
    0.06
     clicking
    0.06
     Questions
    0.06
     nécess
    0.06
    >";
↵
    0.06
    \Category
    0.06
    Activations Density 0.068%

    No Known Activations