© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 28796
    Prev
    Next
    INDEX
    Explanations

    Questions and exclamations

    np_max-act · gemini-2.0-flash

    Tokens that belong to or mark the assistant's response (i.e., assistant-role/generated reply text).

    oai_token-act-pair · gpt-5-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     prize
    -0.07
    센터
    -0.07
     Den
    -0.07
     Prize
    -0.07
    _suite
    -0.06
     Maggie
    -0.06
     aluminum
    -0.06
     pattern
    -0.06
    (check
    -0.06
    煤
    -0.06
    POSITIVE LOGITS
     erotica
    0.07
    otope
    0.06
    なる
    0.06
    攻
    0.06
     recover
    0.06
    λλ
    0.06
    OLVE
    0.06
     CGAffineTransform
    0.06
     onUpdate
    0.06
     апп
    0.06
    Activations Density 0.060%

    No Known Activations