© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58360
    Prev
    Next
    INDEX
    Explanations

    flammability and combustion

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects mentions of fire‐ and explosion‐related hazards (e.g. flammability, ignition, and explosion risks).

    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
    Queue
    -0.07
    .baomidou
    -0.07
    盛
    -0.07
    |array
    -0.07
    Gas
    -0.07
     Thanh
    -0.06
     nums
    -0.06
    [table
    -0.06
    แ
    -0.06
     Multi
    -0.06
    POSITIVE LOGITS
    рощ
    0.07
    批
    0.06
    CoreApplication
    0.06
    IK
    0.06
     latch
    0.06
     dangling
    0.06
     sku
    0.06
    avenous
    0.06
     aplik
    0.06
     Included
    0.06
    Activations Density 0.022%

    No Known Activations