© 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 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. 7-RESID-POST-AA
    11. 96567
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seri
    -0.07
     Ji
    -0.07
    SYNC
    -0.07
     bursts
    -0.07
     Rotterdam
    -0.07
     mı
    -0.06
    PERATURE
    -0.06
     Tenn
    -0.06
     robber
    -0.06
     QUAL
    -0.06
    POSITIVE LOGITS
    Expected
    0.06
     (($
    0.06
    	ff
    0.06
     Valencia
    0.06
    ＠
    0.06
    ++){↵
    0.06
    dark
    0.06
    &display
    0.06
    _dem
    0.06
    (interval
    0.06
    Activations Density 0.020%

    No Known Activations