© 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. 125955
    Prev
    Next
    INDEX
    Explanations

    crime scenes, dead bodies

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on words describing violent crime reports—especially homicide details like murdered, stabbed, body, found, and related scene descriptors.

    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
    -cur
    -0.06
    .='<
    -0.06
    bler
    -0.06
    entities
    -0.06
     statement
    -0.06
    ์ต
    -0.06
    Which
    -0.06
     Noir
    -0.06
    敵
    -0.06
     نظری
    -0.06
    POSITIVE LOGITS
     нек
    0.07
    ython
    0.07
     inaugural
    0.07
     RA
    0.07
     Lower
    0.06
    Untitled
    0.06
     recibir
    0.06
    /lab
    0.06
     Assad
    0.06
    910
    0.06
    Activations Density 0.017%

    No Known Activations