© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54099
    Prev
    Next
    INDEX
    Explanations

    ...

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “files” (especially in API calls like “get the files” or using a `files` property) in multipart/form-data 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
     생산
    -0.07
     Codes
    -0.07
    _mx
    -0.06
    _function
    -0.06
     smarter
    -0.06
    ö
    -0.06
     clock
    -0.06
    SKU
    -0.06
    _ic
    -0.06
    668
    -0.06
    POSITIVE LOGITS
    』（
    0.07
    mazon
    0.06
    >Main
    0.06
     intermediary
    0.06
     مد
    0.06
     đặc
    0.06
    _ball
    0.06
     instructional
    0.06
     béné
    0.06
    larıyla
    0.06
    Activations Density 0.091%

    No Known Activations