© 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. 43389
    Prev
    Next
    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on the numeric list markers (e.g. “1.”, “2.”, “3.”, “Question 1:”, etc.), i.e. tokens that signal numbered enumeration in a quiz or question list.

    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
    (lhs
    -0.07
    _FRAME
    -0.06
    versible
    -0.06
    основ
    -0.06
    изнес
    -0.06
     Localization
    -0.06
     giz
    -0.06
     Shuttle
    -0.06
     Rever
    -0.06
    iyim
    -0.06
    POSITIVE LOGITS
    ACT
    0.07
    bler
    0.07
     sovereignty
    0.07
    yc
    0.06
    ीमत
    0.06
    .agent
    0.06
    /extensions
    0.06
     amend
    0.06
     readonly
    0.06
    .index
    0.06
    Activations Density 0.029%

    No Known Activations