© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12662
    Prev
    Next
    INDEX
    Explanations

    Geometry

    np_max-act · gemini-2.0-flash

    mathematical equations and relationships involving geometric figures.

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

    This neuron detects bits of LaTeX-style mathematical notation (e.g. dollar signs, backslashes, equation 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
    .object
    -0.06
     Ses
    -0.06
    leaflet
    -0.06
    ř
    -0.06
     offic
    -0.06
    -mon
    -0.06
     답
    -0.06
     trous
    -0.06
    subscription
    -0.06
     biomedical
    -0.06
    POSITIVE LOGITS
     {$
    0.07
     cinsel
    0.07
    ;;;;;;;;
    0.06
    #![
    0.06
     sonucu
    0.06
    екси
    0.06
    enství
    0.06
     pleading
    0.06
    ือน
    0.06
     …
    0.06
    Activations Density 0.014%

    No Known Activations