© 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. 128721
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (integers or decimals), i.e. it detects numbers 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
    gap
    -0.07
     pronounced
    -0.07
     Oral
    -0.07
     Covers
    -0.07
    Prior
    -0.06
     null
    -0.06
     depleted
    -0.06
     Saturdays
    -0.06
     Mul
    -0.06
    ixer
    -0.06
    POSITIVE LOGITS
    ").
    0.06
     jenis
    0.06
    (team
    0.06
     nieu
    0.06
     orada
    0.06
    __↵↵
    0.06
    /e
    0.06
    �
    0.06
     česk
    0.06
    /terms
    0.06
    Activations Density 0.073%

    No Known Activations