© 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. 23-RESID-POST-AA
    11. 105561
    Prev
    Next
    INDEX
    Explanations

    то

    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
    _fault
    -0.06
     nedeni
    -0.06
     manners
    -0.06
    (mutex
    -0.06
    _Remove
    -0.06
     artillery
    -0.06
     downfall
    -0.06
     Brady
    -0.06
     lessen
    -0.06
    วาง
    -0.06
    POSITIVE LOGITS
     Pg
    0.06
    ：“
    0.06
     Practices
    0.06
    \xf
    0.06
     burst
    0.06
    عة
    0.06
    ResourceManager
    0.06
     mot
    0.06
    )],↵
    0.06
     Xt
    0.06
    Activations Density 0.085%

    No Known Activations