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. 60964
    Prev
    Next
    INDEX
    Explanations

    scientific theories

    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
     Zh
    -0.07
    Direct
    -0.06
    Positions
    -0.06
    Syn
    -0.06
    iman
    -0.06
     Буд
    -0.06
     expressions
    -0.06
    xi
    -0.06
    ǐ
    -0.06
    ł
    -0.05
    POSITIVE LOGITS
    ='{
    0.07
    .getOwnPropertyDescriptor
    0.07
     healthier
    0.07
    .gsub
    0.07
     ;
    0.07
     زیرا
    0.07
    .effects
    0.06
     OkHttpClient
    0.06
    ันธ
    0.06
    (forms
    0.06
    Activations Density 0.193%

    No Known Activations