© 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. 126760
    Prev
    Next
    INDEX
    Explanations

    craft

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to crafting activities and craft‐related terms (e.g., “craft,” “crafting,” “DIY”).

    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
    daf
    -0.06
    цеп
    -0.06
    abbo
    -0.06
    rieve
    -0.06
    timer
    -0.06
    дет
    -0.06
     Properties
    -0.06
    vier
    -0.05
     ayar
    -0.05
     Levine
    -0.05
    POSITIVE LOGITS
     FB
    0.07
     Welcome
    0.07
     Desert
    0.07
     Rec
    0.07
     Sınıf
    0.07
    _segment
    0.07
    .Wrap
    0.06
    pletion
    0.06
     Crafts
    0.06
     slime
    0.06
    Activations Density 0.053%

    No Known Activations