© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94370
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Vlad" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /loose
    -0.07
    allon
    -0.06
    ÃŃte
    -0.06
    .UnitTesting
    -0.06
    adera
    -0.06
    erialize
    -0.06
    pling
    -0.05
    Å¡il
    -0.05
    era
    -0.05
    illy
    -0.05
    POSITIVE LOGITS
    imir
    0.12
    enburg
    0.08
     Roose
    0.07
    heck
    0.07
    DEST
    0.07
    anova
    0.07
    ÑĸмÑĸ
    0.07
    emin
    0.07
    моÑĢ
    0.07
    enberg
    0.07
    Activations Density 0.016%

    No Known Activations