© 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. 92321
    Prev
    Next
    INDEX
    Explanations

    cameras

    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
     Yankee
    -0.08
     só
    -0.07
    sal
    -0.06
    空
    -0.06
     Dortmund
    -0.06
    ystal
    -0.06
     sea
    -0.06
    Cop
    -0.06
    _pop
    -0.06
     traveller
    -0.06
    POSITIVE LOGITS
     ارسال
    0.06
    $form
    0.06
    ><?=$
    0.06
     BitmapFactory
    0.06
     caching
    0.06
    slack
    0.06
    there
    0.06
     ListBox
    0.06
     LogLevel
    0.06
     cómo
    0.06
    Activations Density 0.021%

    No Known Activations