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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27954
    Prev
    Next
    INDEX
    Explanations

    captcha

    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
    Remember
    -0.06
    ==="
    -0.06
     측
    -0.06
     errorCallback
    -0.06
    Interesting
    -0.06
     majestic
    -0.06
     distinctions
    -0.06
    _ll
    -0.06
    /Area
    -0.06
    (world
    -0.06
    POSITIVE LOGITS
     영화
    0.06
     wegen
    0.06
    <|begin_of_text|>
    0.06
     Charg
    0.06
     carrots
    0.06
     Dennis
    0.06
     että
    0.06
    %">↵
    0.06
     sports
    0.06
     Detective
    0.06
    Activations Density 0.002%

    No Known Activations