© 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. 17534
    Prev
    Next
    INDEX
    Explanations

    trend

    np_max-act · gemini-2.0-flash

    terminology related to battery technology and charging systems.

    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
     Hampshire
    -0.06
     chois
    -0.06
    /key
    -0.06
    runner
    -0.06
    िस
    -0.06
     shielding
    -0.06
     closes
    -0.06
    ，但是
    -0.06
    ckill
    -0.06
    adi
    -0.06
    POSITIVE LOGITS
     '__
    0.07
    IRM
    0.07
    )){
↵
    0.06
    asyarak
    0.06
     ustanov
    0.06
    ReactDOM
    0.06
    )._
    0.06
     Refresh
    0.06
     '_
    0.06
    Searching
    0.06
    Activations Density 0.018%

    No Known Activations