© 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. 11-RESID-POST-AA
    11. 17501
    Prev
    Next
    INDEX
    Explanations

    from

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    negative
    -0.07
    ائج
    -0.07
     Xunit
    -0.06
    иту
    -0.06
     Του
    -0.06
     titanium
    -0.06
    checksum
    -0.06
    -unit
    -0.06
    uspended
    -0.06
     repression
    -0.06
    POSITIVE LOGITS
     EOF
    0.07
    @Json
    0.06
     newline
    0.06
    定义
    0.06
    /script
    0.06
     lurking
    0.06
     quieres
    0.06
     FILES
    0.06
     filament
    0.06
    对方
    0.06
    Activations Density 0.024%

    No Known Activations