© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7971
    Prev
    Next
    INDEX
    Explanations

    Omitted

    np_max-act · gemini-2.0-flash

    This neuron detects parenthetical editorial notes indicating omitted citations or quotation marks (e.g., “(citation and internal quotation marks omitted)”).

    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
    ení
    -0.06
     İran
    -0.06
    デル
    -0.06
     furry
    -0.06
    ्रदर
    -0.06
     Kore
    -0.06
    届
    -0.06
    ۲۰۲
    -0.06
     Light
    -0.06
    RPC
    -0.06
    POSITIVE LOGITS
     omitted
    0.07
     Bram
    0.07
    uplicated
    0.06
     Demir
    0.06
     splice
    0.06
     Киє
    0.06
    Argument
    0.06
    _FORMAT
    0.06
    .setVisibility
    0.06
     scrambled
    0.06
    Activations Density 0.000%

    No Known Activations