© 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. 129854
    Prev
    Next
    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash

    This neuron detects evaluative language—words expressing necessity, requirement, or degree of importance (e.g. “is essential,” “may be required,” “depends”).

    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
    Generated
    -0.06
     aren
    -0.06
    圧
    -0.06
     pays
    -0.06
    _FLAG
    -0.06
    colon
    -0.06
    getPlayer
    -0.06
    Award
    -0.06
    stone
    -0.06
    /cl
    -0.06
    POSITIVE LOGITS
    .communic
    0.06
     nonexistent
    0.06
     accelerometer
    0.06
     RUNNING
    0.06
    ุงเทพ
    0.06
     Christine
    0.06
     resolver
    0.06
     общ
    0.06
    'em
    0.06
     ero
    0.06
    Activations Density 0.197%

    No Known Activations