© 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. 15-LLAMASCOPE-RES-131K
    11. 88062
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to materials and their properties

    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
    mez
    -0.07
     Blank
    -0.07
     vag
    -0.07
     Mint
    -0.07
    mall
    -0.07
    arger
    -0.06
    uide
    -0.06
    jej
    -0.06
    LOS
    -0.06
    ror
    -0.06
    POSITIVE LOGITS
    enga
    0.08
     stress
    0.07
     Stress
    0.07
    stress
    0.07
     stresses
    0.07
    ewn
    0.07
     Coh
    0.06
     initiation
    0.06
     strain
    0.06
     Rolled
    0.06
    Activations Density 0.011%

    No Known Activations