© 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. 57656
    Prev
    Next
    INDEX
    Explanations

    prove

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs that introduce or announce main results (e.g. “prove,” “show,” “give a proof”) in academic writing.

    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
     recycling
    -0.07
    Interactive
    -0.06
     Agility
    -0.06
     seasoned
    -0.06
    圳
    -0.06
     Chip
    -0.06
     konusunda
    -0.06
    ุดท
    -0.06
    ()}</
    -0.06
    Street
    -0.06
    POSITIVE LOGITS
    âl
    0.07
    pee
    0.07
    95
    0.07
    рав
    0.06
    vascular
    0.06
    -block
    0.06
     any
    0.06
    (ur
    0.06
    istence
    0.06
     ports
    0.06
    Activations Density 0.009%

    No Known Activations