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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58196
    Prev
    Next
    INDEX
    Explanations

    Legal documents dismissal

    np_max-act · gemini-2.0-flash

    the neuron identifies bits of legal‐opinion boilerplate—especially tokens from appellate‐rule or statute citations (e.g. “R. App. P.,” “U.S.C.,” “jur”) and disposition words like “DISMISSED” or “PER CURIAM.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    legal terminology and phrases related to court rulings and appeals.

    oai_token-act-pair · gpt-4o-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
     potion
    -0.07
    	RTCK
    -0.07
    دان
    -0.07
    planes
    -0.07
    prd
    -0.07
    suspend
    -0.06
    please
    -0.06
    haven
    -0.06
    .R
    -0.06
    xde
    -0.06
    POSITIVE LOGITS
    References
    0.07
     WideString
    0.07
     Costco
    0.07
     ↵↵↵↵↵
    0.06
     таблет
    0.06
    ScrollBar
    0.06
    수로
    0.06
    LAG
    0.06
     incr
    0.06
     assessing
    0.06
    Activations Density 0.014%

    No Known Activations