© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129815
    Prev
    Next
    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX‐style math notation (e.g. commands like “\mathbb,” “\sqrt,” and the surrounding brackets) that marks mathematical expressions.

    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
    Redux
    -0.08
     Ruf
    -0.07
    iera
    -0.07
     заболева
    -0.07
    ziej
    -0.06
    _gamma
    -0.06
    ků
    -0.06
    OX
    -0.06
    -kit
    -0.06
    cers
    -0.06
    POSITIVE LOGITS
     факт
    0.07
     interracial
    0.06
     imperative
    0.06
    (private
    0.06
     probably
    0.06
     predicates
    0.06
    _SINGLE
    0.06
     pubkey
    0.06
     Random
    0.06
     suppressing
    0.06
    Activations Density 0.002%

    No Known Activations