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. 84415
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    legal terminology related to negligence and liability in insurance cases.

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

    This neuron fires on the little parenthetical sub-clause markers and their labels (e.g. the “(a) …,” “(b) …,” “(c) …” style annotations) in legal text.

    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
    their
    -0.07
    饮
    -0.06
    OSH
    -0.06
    YES
    -0.06
     farewell
    -0.06
    ="--
    -0.06
     خدا
    -0.06
    AI
    -0.06
    vars
    -0.06
    meyi
    -0.06
    POSITIVE LOGITS
     Elect
    0.06
    .isOpen
    0.06
     insight
    0.06
    Compact
    0.06
     convert
    0.06
     Pron
    0.06
     Passage
    0.06
    rowning
    0.06
     ομάδα
    0.06
    ér
    0.06
    Activations Density 0.027%

    No Known Activations