© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24594
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    tokens that mark special structural/control boundaries in the chat/document format (e.g., header/start/end markers).

    oai_token-act-pair · gpt-5-mini
    Triggered 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
    Negative Logits
     Range
    -0.07
    20
    -0.06
     Sw
    -0.06
    18
    -0.06
     humble
    -0.06
     sampled
    -0.06
     awakening
    -0.06
    wk
    -0.06
    Max
    -0.06
    70
    -0.06
    POSITIVE LOGITS
    ces
    0.07
     Methods
    0.06
     aficion
    0.06
     Woj
    0.06
     laughing
    0.06
    .recipe
    0.06
     Мож
    0.06
    createElement
    0.06
    μερο
    0.06
     ini
    0.06
    Activations Density 0.756%

    No Known Activations