© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 113799
    Prev
    Next
    INDEX
    Explanations

    quoted text

    np_max-act · gemini-2.0-flash

    Lines or tokens that mark quoted/replied text in email or forum threads (e.g., leading ">" and "wrote:" markers).

    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
     الصف
    -0.08
     refill
    -0.07
     الرو
    -0.07
     KeyboardInterrupt
    -0.07
    夫
    -0.06
     slows
    -0.06
    Specify
    -0.06
    combo
    -0.06
     worship
    -0.06
     خدم
    -0.06
    POSITIVE LOGITS
    <decimal
    0.07
     ULONG
    0.07
    ccess
    0.06
    outil
    0.06
     tack
    0.06
    LOAT
    0.06
     thiệu
    0.06
    urry
    0.06
    ologne
    0.06
    thew
    0.06
    Activations Density 0.004%

    No Known Activations