© 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. 13373
    Prev
    Next
    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash

    The neuron activates on file-extension names (e.g. png, jpg, gif, svg, woff, etc.) in regex or loader-configuration 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
    失败
    -0.06
     Richardson
    -0.06
    =search
    -0.06
     rotating
    -0.06
    ouro
    -0.06
     يست
    -0.06
    Grid
    -0.06
    -ish
    -0.05
     glBegin
    -0.05
    agan
    -0.05
    POSITIVE LOGITS
    toBeInTheDocument
    0.08
    px
    0.07
     Mitgli
    0.07
     Anime
    0.07
    Ens
    0.07
     cev
    0.07
    сии
    0.07
     모집
    0.07
     Collective
    0.07
    _atts
    0.07
    Activations Density 0.004%

    No Known Activations