Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 15110
    Prev
    Next
    INDEX
    Explanations

    First-person pronouns/verbs

    np_max-act · gemini-2.0-flash

    sentences or clauses containing first-person pronouns (especially "I" / "My") — i.e., author statements about their actions or issues.

    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
    paint
    -0.07
     Hospitality
    -0.06
     заходів
    -0.06
    CHIP
    -0.06
    Zip
    -0.06
     cuisine
    -0.06
     เซ
    -0.06
    _type
    -0.06
    哭
    -0.06
    바이
    -0.06
    POSITIVE LOGITS
     JsonResponse
    0.06
     prostituer
    0.06
    _LED
    0.06
    .Obj
    0.06
     шту
    0.06
     Am
    0.06
     وكانت
    0.06
    )?;↵↵
    0.06
    .SendMessage
    0.06
     використання
    0.06
    Activations Density 0.230%

    No Known Activations