© 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. 11-RESID-POST-AA
    11. 101207
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    end-of-sentence punctuation, especially periods marking sentence boundaries.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
    Negative Logits
    .itemView
    -0.06
    ocomplete
    -0.06
     "'.$
    -0.06
    .spinner
    -0.06
    urnal
    -0.06
     adulthood
    -0.06
    еф
    -0.06
    -room
    -0.06
    ached
    -0.06
    >k
    -0.06
    POSITIVE LOGITS
    حاد
    0.06
    -div
    0.06
    фф
    0.06
    =edge
    0.06
     harmon
    0.06
     OSC
    0.06
    irler
    0.06
    .quant
    0.06
    低
    0.06
     Assad
    0.06
    Activations Density 0.192%

    No Known Activations