© 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. 59299
    Prev
    Next
    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of curly-brace placeholders (i.e. `{…}` tokens) in code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    izada
    -0.06
    (idx
    -0.06
     misplaced
    -0.06
     řid
    -0.06
     '&#
    -0.05
     reputed
    -0.05
     jpg
    -0.05
     आप
    -0.05
     cổ
    -0.05
    _fps
    -0.05
    POSITIVE LOGITS
    .pack
    0.07
     warmly
    0.07
     Tarih
    0.07
     EXTRA
    0.07
     kickoff
    0.07
    alleng
    0.07
     Neg
    0.06
     HT
    0.06
    데이트
    0.06
     disparate
    0.06
    Activations Density 0.004%

    No Known Activations