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. 21837
    Prev
    Next
    INDEX
    Explanations

    Legal contexts

    np_max-act · gemini-2.0-flash

    references to legal cases and rulings related to employment and labor laws.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to mentions of a case or matter being “pending,” i.e. the word “pending” in a legal procedural context.

    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
    .crt
    -0.07
    ีซ
    -0.07
    pcodes
    -0.07
    Contain
    -0.06
     thỏa
    -0.06
    گیری
    -0.06
    Opt
    -0.06
     Shiv
    -0.06
    きた
    -0.06
    /********************************************************************************
    -0.06
    POSITIVE LOGITS
    imonial
    0.07
     harmon
    0.07
     interventions
    0.06
    (single
    0.06
     تعد
    0.06
     experiment
    0.06
    	up
    0.06
     Evening
    0.06
     veterinarian
    0.06
    	assertNotNull
    0.06
    Activations Density 0.026%

    No Known Activations