© 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. 77019
    Prev
    Next
    INDEX
    Explanations

    hospital infections

    np_max-act · gemini-2.0-flash

    information related to Clostridium difficile infection and its impacts on public health.

    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
    );;↵
    -0.07
    _java
    -0.07
    ibaba
    -0.06
    ErrorHandler
    -0.06
    )item
    -0.06
     adding
    -0.06
    igr
    -0.06
     wrestler
    -0.06
     Essay
    -0.06
     ارائه
    -0.06
    POSITIVE LOGITS
     závod
    0.07
     Government
    0.07
     Filme
    0.06
     invading
    0.06
     دقی
    0.06
     Mayıs
    0.06
     medical
    0.06
    .precision
    0.06
     Unlimited
    0.06
    .switch
    0.06
    Activations Density 0.021%

    No Known Activations