© 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. 78840
    Prev
    Next
    INDEX
    Explanations

    guard

    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
    Api
    -0.07
    .isNotEmpty
    -0.07
    米
    -0.07
    Open
    -0.07
     Theme
    -0.07
    actical
    -0.06
     Bottle
    -0.06
     place
    -0.06
     tel
    -0.06
    =fopen
    -0.06
    POSITIVE LOGITS
     guard
    0.10
     Guardian
    0.10
     Guard
    0.10
     guards
    0.09
    Guard
    0.09
    -guard
    0.09
     Guardians
    0.09
     guarding
    0.08
     guardians
    0.08
     Guards
    0.07
    Activations Density 0.017%

    No Known Activations