© 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. 15-RESID-POST-AA
    11. 106915
    Prev
    Next
    INDEX
    Explanations

    Words ending in "ing"

    np_max-act · gemini-2.0-flash

    spots words and phrases that indicate creating, developing, preparing, or meticulous effort (work-in-progress and craftsmanship).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cy
    -0.06
     Increasing
    -0.06
    @foreach
    -0.06
     بسیار
    -0.06
     extremely
    -0.06
     nouveaux
    -0.06
     continuum
    -0.06
    eof
    -0.06
    fold
    -0.06
     інститут
    -0.06
    POSITIVE LOGITS
     Replace
    0.06
    atches
    0.06
    -CP
    0.06
    _supp
    0.06
    apers
    0.06
    ARENT
    0.06
    PR
    0.06
     survivor
    0.06
    &W
    0.06
    izza
    0.06
    Activations Density 0.066%

    No Known Activations