© 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
    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. 44735
    Prev
    Next
    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric and quantitative expressions, spotting numbers (including decimals and percentages) and their surrounding comparison context.

    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
     POW
    -0.06
    _updated
    -0.06
     Salvador
    -0.06
     beb
    -0.06
    ascal
    -0.06
     swirl
    -0.06
    �
    -0.06
     electro
    -0.06
     anlamda
    -0.06
    -${
    -0.05
    POSITIVE LOGITS
    AuthToken
    0.07
    Chart
    0.07
    _keeper
    0.06
    partials
    0.06
    ”，
    0.06
     adventures
    0.06
    (CharSequence
    0.06
     ----------↵
    0.06
    형
    0.06
    steller
    0.06
    Activations Density 0.055%

    No Known Activations