© 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. 54515
    Prev
    Next
    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens—especially floating‐point numbers (e.g. decimal values in parentheses for ranges, means, follow-up times, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions on surgical outcomes and complications related to limb operations.

    oai_token-act-pair · gpt-4o-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
    ίλ
    -0.07
    dddd
    -0.06
    iała
    -0.06
    انگ
    -0.06
     irrational
    -0.06
    imized
    -0.06
    ownership
    -0.06
    ailing
    -0.06
    جم
    -0.06
    Fade
    -0.06
    POSITIVE LOGITS
    辺
    0.07
     홈
    0.06
     encompasses
    0.06
     bas
    0.06
     Dolphins
    0.06
     dolphins
    0.06
     боль
    0.06
     متن
    0.06
    障
    0.06
     tonight
    0.06
    Activations Density 0.004%

    No Known Activations