© 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. 73792
    Prev
    Next
    INDEX
    Explanations

    crafting materials

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of craft materials and supplies (e.g., paper, cardstock, card, Prima papers, ribbon, foam).

    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
    image
    -0.06
    OBJECT
    -0.06
    client
    -0.06
     Overview
    -0.06
    onDelete
    -0.06
     onDataChange
    -0.06
    .innerHTML
    -0.06
    >Error
    -0.06
     COMPLETE
    -0.06
    olulu
    -0.06
    POSITIVE LOGITS
     Benn
    0.08
    apanese
    0.07
    _private
    0.07
    Sexy
    0.06
    ouver
    0.06
     tip
    0.06
     langue
    0.06
     schn
    0.06
    nosti
    0.06
    ços
    0.06
    Activations Density 0.019%

    No Known Activations