© 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
    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. 27592
    Prev
    Next
    INDEX
    Explanations

    years and the number 2

    np_max-act · gemini-2.0-flash
    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
    Py
    -0.07
    .findall
    -0.06
    ảy
    -0.06
    ینی
    -0.06
     highs
    -0.06
     yanlış
    -0.06
    нюю
    -0.06
    .BorderFactory
    -0.06
     год
    -0.06
     daily
    -0.06
    POSITIVE LOGITS
    (panel
    0.07
    .labels
    0.07
    <option
    0.06
    dirname
    0.06
     ремон
    0.06
     warranties
    0.06
     fab
    0.06
     мистецт
    0.06
     Carlos
    0.06
    Howard
    0.06
    Activations Density 0.002%

    No Known Activations