© 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. 90838
    Prev
    Next
    INDEX
    Explanations

    game abilities and activation

    np_max-act · gemini-2.0-flash

    This neuron spotlights numeric values and units (e.g., damage amounts, durations, cooldowns, percentages) in game‐ability descriptions.

    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
    肩
    -0.07
     Congressional
    -0.07
     Stout
    -0.07
     conceived
    -0.07
     implies
    -0.06
    iosis
    -0.06
     tul
    -0.06
     sword
    -0.06
    putation
    -0.06
    knowledge
    -0.06
    POSITIVE LOGITS
     Tỉnh
    0.07
    toBeInTheDocument
    0.07
    ектор
    0.06
     Atmos
    0.06
    ertz
    0.06
     nást
    0.06
    .TestCheck
    0.06
     IEntity
    0.06
    auté
    0.06
    Donate
    0.06
    Activations Density 0.008%

    No Known Activations