© 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. 23215
    Prev
    Next
    INDEX
    Explanations

    enable

    np_max-act · gemini-2.0-flash

    formal business terminology related to company analysis and strategic planning.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     ballpark
    -0.07
     quận
    -0.07
     Karlov
    -0.07
     sucks
    -0.07
     rule
    -0.07
    提
    -0.06
     suspicious
    -0.06
     caratter
    -0.06
     pravděpodob
    -0.06
     altri
    -0.06
    POSITIVE LOGITS
     enable
    0.12
     enables
    0.10
     enabling
    0.09
     enabled
    0.07
    -enabled
    0.07
    支援
    0.07
    чес
    0.07
    สง
    0.07
    ="'.$
    0.07
     ensuring
    0.07
    Activations Density 0.009%

    No Known Activations