© 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. 59115
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to the model’s internal conversation‐format control tokens (e.g. end‐of‐text and header delimiters) rather than ordinary words.

    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
    _CHUNK
    -0.07
    -foot
    -0.07
    .x
    -0.07
    err
    -0.07
    meaning
    -0.07
    _RESET
    -0.07
    _relu
    -0.06
     определен
    -0.06
    くん
    -0.06
    _training
    -0.06
    POSITIVE LOGITS
     initialValue
    0.07
    urchases
    0.06
    创新
    0.06
    natural
    0.06
     قانون
    0.06
     podle
    0.06
     khác
    0.06
     услуг
    0.05
     renaming
    0.05
     เล
    0.05
    Activations Density 0.082%

    No Known Activations