© 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. 27-RESID-POST-AA
    11. 44787
    Prev
    Next
    INDEX
    Explanations

    请

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tắc
    -0.06
     материал
    -0.06
     +/-
    -0.06
    ریم
    -0.06
     rtn
    -0.06
    262
    -0.06
    approximately
    -0.06
     kra
    -0.06
     gypsum
    -0.06
     zou
    -0.06
    POSITIVE LOGITS
    odie
    0.07
    .perform
    0.06
     DDR
    0.06
    balanced
    0.06
     conveyed
    0.06
     Humph
    0.06
    ibrary
    0.06
     trước
    0.06
     MessageType
    0.06
     mistr
    0.06
    Activations Density 0.004%

    No Known Activations