© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 108323
    Prev
    Next
    INDEX
    Explanations

    guard

    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_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
     ド
    -0.08
     ordinal
    -0.07
    馬
    -0.07
     freezing
    -0.07
     ano
    -0.07
     швидко
    -0.07
    "H
    -0.07
     Ром
    -0.06
    ньо
    -0.06
    <Book
    -0.06
    POSITIVE LOGITS
     protect
    0.07
     bere
    0.07
    $(".
    0.06
     excessive
    0.06
    ---@
    0.06
    --↵
    0.06
    nostic
    0.06
    ARENT
    0.06
     innocence
    0.06
    _inactive
    0.06
    Activations Density 0.028%

    No Known Activations