© 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. 55955
    Prev
    Next
    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash

    This neuron activates on technical mathematical terminology—especially words naming function properties (like “homomorphism,” “measurable,” “continuous,” etc.) in theorem‐style contexts.

    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
    .ke
    -0.07
    Finish
    -0.07
    .sprites
    -0.06
    อนไลน
    -0.06
     alist
    -0.06
    018
    -0.06
    feof
    -0.06
    .len
    -0.06
    교회
    -0.06
    @$
    -0.06
    POSITIVE LOGITS
     �
    0.07
    _BOTH
    0.07
     relied
    0.06
     Ens
    0.06
     jot
    0.06
     detailing
    0.06
    ЕТ
    0.06
     brewery
    0.06
    Tipo
    0.06
     ac
    0.06
    Activations Density 0.004%

    No Known Activations