© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13600
    Prev
    Next
    INDEX
    Explanations

    closed

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of things being "closed" (often in the context of a closed system or loop).

    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
    工
    -0.07
     metic
    -0.06
    _proc
    -0.06
    ':{'
    -0.06
     discard
    -0.06
     Hercules
    -0.06
    Bulk
    -0.06
    (Component
    -0.06
    Walk
    -0.06
    Outputs
    -0.06
    POSITIVE LOGITS
    ução
    0.07
    "is
    0.07
    /blue
    0.07
     inverted
    0.06
     بیماری
    0.06
    developer
    0.06
    یدا
    0.06
    ＠
    0.06
     Bayesian
    0.06
     Algorithm
    0.06
    Activations Density 0.006%

    No Known Activations