© 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. 85533
    Prev
    Next
    INDEX
    Explanations

    references to research and proposals within scientific literature

    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
    ayne
    -0.08
    oram
    -0.07
    tÃŃ
    -0.07
    utin
    -0.07
    ymes
    -0.07
    isure
    -0.07
    kel
    -0.07
    pector
    -0.07
    znám
    -0.07
    reib
    -0.06
    POSITIVE LOGITS
     recently
    0.07
     earlier
    0.07
     Garn
    0.07
    recent
    0.07
     recent
    0.06
     liter
    0.06
     elsewhere
    0.06
    POSE
    0.06
    ro
    0.06
     Hughes
    0.06
    Activations Density 0.035%

    No Known Activations