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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89591
    Prev
    Next
    INDEX
    Explanations

    claim

    np_max-act · gemini-2.0-flash

    mathematical proofs and reasoning in set theory.

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

    This neuron detects LaTeX‐style mathematical notation (e.g. backslashes, math symbols, and formula fragments).

    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
    吨
    -0.07
    헤
    -0.07
     гара
    -0.07
     underwear
    -0.07
     boca
    -0.06
    cook
    -0.06
     grant
    -0.06
    markup
    -0.06
     ==>
    -0.06
     лишь
    -0.06
    POSITIVE LOGITS
    raid
    0.06
    ://${
    0.06
     solidarity
    0.06
     carved
    0.06
    				
    0.06
     Lois
    0.06
     мо
    0.06
    ει
    0.06
    urls
    0.06
    ensively
    0.06
    Activations Density 0.022%

    No Known Activations