© 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. 54413
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron responds to hyphenated numeric patterns—i.e. sports‐style scorelines (e.g. “13-0,” “3-2,” “17-1”).

    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
    розум
    -0.06
    ="<
    -0.06
     bắt
    -0.06
    终
    -0.06
     bitmask
    -0.06
     Beam
    -0.06
    ',{
    -0.06
    )}>
    -0.06
     rounding
    -0.06
     ashes
    -0.06
    POSITIVE LOGITS
    REV
    0.07
     Identification
    0.06
     Jak
    0.06
    TEGR
    0.06
     medically
    0.06
    <Response
    0.06
    stagram
    0.06
    Hey
    0.06
     کار
    0.06
     uniqueness
    0.06
    Activations Density 0.009%

    No Known Activations