© 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. 23-RESID-POST-AA
    11. 67494
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undermining
    -0.07
     catastrophic
    -0.07
     undermines
    -0.07
     affects
    -0.07
     hydro
    -0.07
    Чтобы
    -0.06
     undermined
    -0.06
    (concat
    -0.06
    '↵↵↵↵
    -0.06
    重複重複
    -0.06
    POSITIVE LOGITS
     mise
    0.07
     misses
    0.06
     Gamer
    0.06
    ář
    0.06
    ertoire
    0.06
    به
    0.06
     istem
    0.06
    λια
    0.06
    rám
    0.06
    evi
    0.06
    Activations Density 0.104%

    No Known Activations