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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 91742
    Prev
    Next
    INDEX
    Explanations

    Well/Yes (Discourse Markers)

    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
     Yen
    -0.07
    ROAD
    -0.06
    _indicator
    -0.06
    函
    -0.06
    าย
    -0.06
    AVIS
    -0.06
    Lin
    -0.06
    afc
    -0.06
     Lin
    -0.05
    ailer
    -0.05
    POSITIVE LOGITS
    ,double
    0.07
    ermann
    0.07
     arrest
    0.07
    �
    0.06
     forIndexPath
    0.06
    年の
    0.06
     affair
    0.06
    _eof
    0.06
    then
    0.06
     cinematic
    0.06
    Activations Density 0.145%

    No Known Activations