© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126322
    Prev
    Next
    INDEX
    Explanations

    destiny

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric tokens written as decimal numbers (floating‐point literals).

    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
     piles
    -0.07
     Polar
    -0.07
    нив
    -0.07
     picture
    -0.07
     burgl
    -0.07
     indexer
    -0.06
     hide
    -0.06
     порт
    -0.06
     art
    -0.06
    WRITE
    -0.06
    POSITIVE LOGITS
     destiny
    0.08
     Destiny
    0.06
     κα
    0.06
     нерв
    0.06
    uly
    0.06
     गलत
    0.06
    ->{$
    0.06
    unched
    0.06
    Venue
    0.06
    -serving
    0.06
    Activations Density 0.025%

    No Known Activations