© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125050
    Prev
    Next
    INDEX
    Explanations

    ce

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX-style chemical notation, i.e. the math delimiters and commands (like “$”, “\ce”, “{”, “}”, etc.) used for typesetting chemical formulas.

    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
    -word
    -0.07
    ゴ
    -0.07
    drivers
    -0.06
     Lexer
    -0.06
    TES
    -0.06
    もない
    -0.06
     이러
    -0.06
     cursor
    -0.06
     Repos
    -0.06
     círk
    -0.06
    POSITIVE LOGITS
     Abb
    0.06
     [=[
    0.06
    ับความ
    0.06
     eventdata
    0.06
    LAB
    0.06
    emy
    0.06
     Trust
    0.06
    (()=>{↵
    0.06
     Carnival
    0.06
    Parameter
    0.06
    Activations Density 0.001%

    No Known Activations