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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 86007
    Prev
    Next
    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash

    This neuron detects the jurisdiction header specifying the court district (e.g. “for the Eastern District of Texas”) in appellate opinions.

    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
     budou
    -0.07
    .req
    -0.07
    _Rem
    -0.07
     sensors
    -0.07
    ;?#
    -0.06
    _member
    -0.06
    Лю
    -0.06
    	ff
    -0.06
     Lup
    -0.06
    _tv
    -0.06
    POSITIVE LOGITS
     металли
    0.07
     GENERAL
    0.06
    irit
    0.06
     křes
    0.06
    eneral
    0.06
     Lester
    0.06
     Petit
    0.06
     लगभग
    0.06
    {}\
    0.05
    kah
    0.05
    Activations Density 0.004%

    No Known Activations