© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 84283
    Prev
    Next
    INDEX
    Explanations

    expressions of unity and togetherness

    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
    WR
    -0.07
    ritz
    -0.07
    velte
    -0.07
    stery
    -0.06
    owania
    -0.06
    dration
    -0.06
     getItemCount
    -0.06
    à¹Īà¸Ńย
    -0.06
    мена
    -0.06
    .plist
    -0.06
    POSITIVE LOGITS
     nhau
    0.08
    kus
    0.08
     Patterson
    0.08
    -sama
    0.08
    /group
    0.07
    oldur
    0.07
    .Guna
    0.07
    /as
    0.07
     Harley
    0.07
    ResultsController
    0.07
    Activations Density 0.008%

    No Known Activations