© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6366
    Prev
    Next
    INDEX
    Explanations

    web sites

    np_max-act · gemini-2.0-flash

    This neuron activates for tokens in the “Browse Website” command sequence (e.g. “browse_website,” “Website,” URL-related tokens).

    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
     کو
    -0.08
     사망
    -0.07
     composition
    -0.07
    probability
    -0.06
    :set
    -0.06
    카
    -0.06
    睛
    -0.06
    .order
    -0.06
     آب
    -0.06
    ({});↵
    -0.06
    POSITIVE LOGITS
    ssi
    0.06
     sentir
    0.06
     соглас
    0.06
    _signed
    0.06
     ici
    0.06
    нед
    0.06
    -sectional
    0.06
     succes
    0.06
    ης
    0.06
    donnees
    0.06
    Activations Density 0.006%

    No Known Activations