Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84930
    Prev
    Next
    INDEX
    Explanations

    prejudicial

    np_max-act · gemini-2.0-flash

    This neuron detects substrings of legal‐procedural error terms—e.g. pieces of words like “mist-…-rial,” “prejud-…-icial,” “jury,” etc.—that appear in judicial opinions describing trial objections and motions.

    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
    Training
    -0.07
     training
    -0.06
     until
    -0.06
    рест
    -0.06
    ปล
    -0.06
     Jean
    -0.06
     reign
    -0.06
    video
    -0.05
    swers
    -0.05
    ileri
    -0.05
    POSITIVE LOGITS
     сегодня
    0.07
    ुबह
    0.07
    elleicht
    0.06
    ="",
    0.06
     Venez
    0.06
     broad
    0.06
    	G
    0.06
     هي
    0.06
     residence
    0.06
     %+
    0.06
    Activations Density 0.003%

    No Known Activations