© 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. 15-RESID-POST-AA
    11. 36831
    Prev
    Next
    INDEX
    Explanations

    Places

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Odkazy
    -0.06
     Integr
    -0.06
     Sidney
    -0.06
     yên
    -0.06
    及
    -0.06
     техничес
    -0.06
     Workflow
    -0.06
     cybersecurity
    -0.06
     gerekli
    -0.06
    _SERVICE
    -0.06
    POSITIVE LOGITS
     susp
    0.06
    isen
    0.06
    ddl
    0.06
     Paging
    0.06
    ({_
    0.06
    tiğini
    0.06
    枚
    0.06
    ouis
    0.06
    DSL
    0.06
    pas
    0.06
    Activations Density 0.123%

    No Known Activations