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

    Neuronpedia

    Jacobian LensNEW
    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. 103331
    Prev
    Next
    INDEX
    Explanations

    Questions and personal stories

    np_max-act · gemini-2.0-flash

    instances of reported speech or quotations (tokens like "said", "says", "told" and surrounding quoted 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_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
    Orden
    -0.07
    umes
    -0.07
    erequisites
    -0.07
    protocols
    -0.07
    amentals
    -0.07
     名
    -0.06
     GG
    -0.06
     inp
    -0.06
    wd
    -0.06
    based
    -0.06
    POSITIVE LOGITS
    dong
    0.07
     Qui
    0.06
    浮
    0.06
     Francie
    0.06
     프로
    0.06
    من
    0.06
     PYTHON
    0.06
    .poly
    0.06
    })",
    0.06
    _tools
    0.06
    Activations Density 0.046%

    No Known Activations