© 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. 11-RESID-POST-AA
    11. 93765
    Prev
    Next
    INDEX
    Explanations

    forum/QA excerpts

    np_max-act · gemini-2.0-flash

    user or assistant role indicators at the beginning of a message.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @chuloivawork
    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
    ่วน
    -0.07
     Daily
    -0.06
    ３
    -0.06
     neurons
    -0.06
    ，默认
    -0.06
     corridor
    -0.06
     INNER
    -0.06
    172
    -0.06
    Whenever
    -0.06
    upon
    -0.06
    POSITIVE LOGITS
    modx
    0.08
    -col
    0.08
    =X
    0.07
    levels
    0.06
    .inventory
    0.06
    $o
    0.06
    unctuation
    0.06
    _coeff
    0.06
    ‪
    0.06
     contrato
    0.06
    Activations Density 0.057%

    No Known Activations