© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47641
    Prev
    Next
    INDEX
    Explanations

    debugging errors

    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
    -core
    -0.06
     ↔
    -0.06
     ώρα
    -0.06
     CancellationToken
    -0.06
    htdocs
    -0.06
    แสง
    -0.06
     Jensen
    -0.06
     UIBarButtonItem
    -0.06
    breadcrumbs
    -0.06
    Checking
    -0.06
    POSITIVE LOGITS
     workforce
    0.07
     골
    0.07
     Lands
    0.07
    _FWD
    0.07
     shredded
    0.07
    _PROM
    0.07
    PushButton
    0.06
    �
    0.06
     Sudan
    0.06
    _compiler
    0.06
    Activations Density 0.004%

    No Known Activations