Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 123136
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
     đọc
    -0.07
    Opened
    -0.06
     누구
    -0.06
    оз
    -0.06
    addPreferredGap
    -0.06
     输
    -0.06
     şaş
    -0.06
     liners
    -0.06
    wrap
    -0.06
    結果
    -0.06
    POSITIVE LOGITS
     WON
    0.07
     DCHECK
    0.07
     attend
    0.06
     Practices
    0.06
     Caf
    0.06
    .borrow
    0.06
     RVA
    0.06
    واع
    0.06
    [js
    0.06
     Beste
    0.05
    Activations Density 0.158%

    No Known Activations