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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 127315
    Prev
    Next
    INDEX
    Explanations

    by

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trajectories
    -0.06
    Patterns
    -0.06
     historian
    -0.06
     marriages
    -0.06
     monument
    -0.06
    แน
    -0.06
     놀
    -0.06
     pilots
    -0.06
    ológ
    -0.06
     yog
    -0.06
    POSITIVE LOGITS
     докум
    0.07
     disappe
    0.07
    [code
    0.07
    ernetes
    0.07
     olmasına
    0.06
     eksik
    0.06
     realizar
    0.06
     rů
    0.06
     Wak
    0.06
    _java
    0.06
    Activations Density 0.011%

    No Known Activations