© 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. 90655
    Prev
    Next
    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash

    This neuron fires on empty‐container literals, i.e. bracket pairs with no content like “()” or “[].”

    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
     ----------------------------------------------------------------------↵
    -0.07
    .MM
    -0.07
    ωμά
    -0.06
    His
    -0.06
    ..."↵↵
    -0.06
    .VISIBLE
    -0.06
    :"",↵
    -0.06
    his
    -0.06
    :absolute
    -0.06
     zien
    -0.06
    POSITIVE LOGITS
     更
    0.07
     procession
    0.07
    dic
    0.07
    нова
    0.07
     Venezuelan
    0.06
     gast
    0.06
    uchi
    0.06
    idious
    0.06
    па
    0.06
     relação
    0.06
    Activations Density 0.017%

    No Known Activations