© 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. 30988
    Prev
    Next
    INDEX
    Explanations

    whole

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of the word “whole,” especially when used as a prefix (e.g. whole-body, whole genome, Whole Foods).

    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
     salsa
    -0.07
    ुग
    -0.06
    _svg
    -0.06
    ��
    -0.06
    .AddModelError
    -0.06
     kB
    -0.06
    ाजप
    -0.06
    ()
↵
↵
    -0.06
     params
    -0.06
    妙
    -0.06
    POSITIVE LOGITS
     Whole
    0.12
    whole
    0.10
    Whole
    0.10
     whole
    0.09
     completeness
    0.07
     Comprehensive
    0.07
    ethe
    0.06
     PURE
    0.06
     �
    0.06
     حي
    0.06
    Activations Density 0.009%

    No Known Activations