© 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. 89060
    Prev
    Next
    INDEX
    Explanations

    exposure

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of occupational chemical exposure (e.g. “exposure to … in workers,” “occupational … asthma,” “workers exposed to …”).

    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
     Wool
    -0.06
     bytes
    -0.06
    .React
    -0.06
    -first
    -0.06
    =function
    -0.06
    毫
    -0.06
    -code
    -0.06
     weil
    -0.06
    平均
    -0.06
     سپس
    -0.06
    POSITIVE LOGITS
     advertised
    0.06
     preprocess
    0.06
     Industrial
    0.06
     secret
    0.06
     الج
    0.06
    Receive
    0.06
    Cour
    0.06
    σματα
    0.06
     soldiers
    0.06
     Johannes
    0.05
    Activations Density 0.016%

    No Known Activations