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. 106162
    Prev
    Next
    INDEX
    Explanations

    Children playing

    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
    ारक
    -0.07
     дв
    -0.07
    ستان
    -0.07
    accessToken
    -0.07
    ζ
    -0.07
     президент
    -0.06
    ylko
    -0.06
    дает
    -0.06
    stu
    -0.06
    이비
    -0.06
    POSITIVE LOGITS
     converts
    0.06
     branching
    0.06
     Cooking
    0.06
     orgán
    0.06
    asına
    0.06
    gan
    0.06
     party
    0.06
    âb
    0.06
    Image
    0.06
    punk
    0.06
    Activations Density 0.016%

    No Known Activations