© 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. 15-RESID-POST-AA
    11. 23401
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    tokens that look like short device/control commands written as uppercase variable assignments (e.g., L=True, T=False, S="...").

    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
     ham
    -0.07
    ston
    -0.07
    'я
    -0.07
    وقيت
    -0.07
     stmt
    -0.07
    cors
    -0.06
    Dou
    -0.06
     database
    -0.06
    573
    -0.06
    ины
    -0.06
    POSITIVE LOGITS
    ุ์
    0.08
    Systems
    0.07
    分析
    0.06
     khoản
    0.06
    spender
    0.06
     BM
    0.06
     Millions
    0.06
     وز
    0.06
    -tech
    0.06
    �
    0.06
    Activations Density 0.232%

    No Known Activations