© 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. 126098
    Prev
    Next
    INDEX
    Explanations

    protagonist

    np_max-act · gemini-2.0-flash

    This neuron activates on words referring to a story’s main character (e.g., “protagonist,” “lead,” “leads”).

    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
    jac
    -0.07
     RESET
    -0.06
    爵
    -0.06
     pregn
    -0.06
    _ipc
    -0.06
     leaned
    -0.06
    -new
    -0.06
    ее
    -0.06
    duck
    -0.06
     princ
    -0.06
    POSITIVE LOGITS
     protagonists
    0.07
     protagon
    0.07
     protagonist
    0.07
     activists
    0.06
     โรง
    0.06
     Chrom
    0.06
    (Login
    0.06
    .events
    0.06
    ulta
    0.06
    /entities
    0.06
    Activations Density 0.013%

    No Known Activations