© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56853
    Prev
    Next
    INDEX
    Explanations

    Common denominators

    np_max-act · gemini-2.0-flash

    This neuron primarily fires on numeric tokens—especially fractional or decimal numbers—within the math problems.

    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
    arrings
    -0.07
    SHARE
    -0.07
    olec
    -0.07
     Democrats
    -0.07
    盒
    -0.07
    thren
    -0.07
     Button
    -0.06
    講
    -0.06
    shot
    -0.06
     checked
    -0.06
    POSITIVE LOGITS
     scept
    0.07
    �始
    0.06
     Saddam
    0.06
    เขา
    0.06
     Meer
    0.06
     ö
    0.06
    _TRUE
    0.06
    ंस
    0.06
    	getline
    0.06
     tensor
    0.05
    Activations Density 0.002%

    No Known Activations