© 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. 8920
    Prev
    Next
    INDEX
    Explanations

    sports games

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on numeric sports statistics and game score lines.

    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
    [count
    -0.07
     Rosen
    -0.07
    HexString
    -0.07
     �
    -0.06
     Compar
    -0.06
     inadequate
    -0.06
     spectator
    -0.06
    Compar
    -0.06
     nep
    -0.06
     Championships
    -0.06
    POSITIVE LOGITS
    参考
    0.08
     integrate
    0.07
     leather
    0.06
    {l
    0.06
     "('
    0.06
    Albert
    0.06
     vex
    0.06
     uso
    0.06
    lıklar
    0.06
     criminals
    0.06
    Activations Density 0.022%

    No Known Activations