© 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. 73930
    Prev
    Next
    INDEX
    Explanations

    woff

    np_max-act · gemini-2.0-flash

    This neuron detects CSS font‐file format tokens (e.g. the “.eot,” “.woff,” “.ttf,” and “.svg” fragments) in @font-face src URLs.

    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
     Yang
    -0.07
    /auth
    -0.06
    Clock
    -0.06
    .mode
    -0.06
    確
    -0.06
    pcodes
    -0.06
    630
    -0.06
    ILD
    -0.06
    -function
    -0.06
    (cursor
    -0.06
    POSITIVE LOGITS
    woff
    0.08
     superiority
    0.07
    OUNT
    0.07
     dred
    0.07
    	EXPECT
    0.07
     olduğuna
    0.07
     Arkansas
    0.06
     HIM
    0.06
     Via
    0.06
     spilled
    0.06
    Activations Density 0.001%

    No Known Activations