© 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. 56886
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (e.g. years, dates, or other numbers).

    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
    ۱۹۴
    -0.08
     mar
    -0.08
     Baz
    -0.07
     relativ
    -0.07
    squ
    -0.07
     Und
    -0.07
     cap
    -0.07
     intervals
    -0.07
     Cou
    -0.07
     eas
    -0.07
    POSITIVE LOGITS
     keep
    0.07
    nl
    0.06
     messy
    0.06
     colorWith
    0.05
    мерикан
    0.05
    =$('#
    0.05
    .Sort
    0.05
     obchodní
    0.05
     بنا
    0.05
    [child
    0.05
    Activations Density 0.156%

    No Known Activations