© 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. 30663
    Prev
    Next
    INDEX
    Explanations

    Particle physics jets

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of (hadronic) jets or jet-related terms in particle-physics collider event descriptions.

    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
     Corn
    -0.07
     Print
    -0.07
    ğına
    -0.07
     inhibitors
    -0.06
     elbows
    -0.06
    iyan
    -0.06
    合同
    -0.06
     paper
    -0.06
     flattened
    -0.06
     contracts
    -0.06
    POSITIVE LOGITS
    cimiento
    0.06
    SED
    0.06
     speed
    0.06
    ندي
    0.06
     групп
    0.06
     grow
    0.06
    адження
    0.06
    .deleteById
    0.06
     شي
    0.06
    okable
    0.06
    Activations Density 0.005%

    No Known Activations