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. 11-RESID-POST-AA
    6. 50336
    Prev
    Next
    INDEX
    Explanations

    document

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    û
    -0.07
     neatly
    -0.06
    Hallo
    -0.06
     REAL
    -0.06
     dospěl
    -0.06
    ception
    -0.06
     prostor
    -0.06
    .SimpleButton
    -0.06
    erd
    -0.06
    .ARR
    -0.06
    POSITIVE LOGITS
    iếng
    0.07
    arbonate
    0.07
     Buenos
    0.07
     liquids
    0.07
     DIR
    0.07
     [
    0.07
    寒
    0.06
     그러
    0.06
    (['
    0.06
     ω
    0.06
    Activations Density 0.002%

    No Known Activations