© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 72253
    Prev
    Next
    INDEX
    Explanations

    Appellant

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the word “Appellant” (i.e. segments of that token) in court‐opinion headings.

    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
     reading
    -0.07
     performed
    -0.07
    Perform
    -0.07
     nucleus
    -0.07
     indicate
    -0.07
     read
    -0.07
    getRepository
    -0.06
     admitted
    -0.06
     też
    -0.06
     perform
    -0.06
    POSITIVE LOGITS
    upo
    0.06
    Pub
    0.06
     stdClass
    0.06
    สอง
    0.06
     Wish
    0.06
     Pew
    0.06
    'er
    0.06
    -version
    0.06
    gets
    0.06
    fighter
    0.06
    Activations Density 0.006%

    No Known Activations