© 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 EvalsExportsinterp-engineNEWAPI 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. 14866
    Prev
    Next
    INDEX
    Explanations

    terms relating to outputs and results in computational contexts

    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
    169
    -0.08
    ewire
    -0.07
     cul
    -0.06
     Tall
    -0.06
     aks
    -0.06
    ump
    -0.06
    is
    -0.06
    oland
    -0.06
    âĦ¢
    -0.06
    missive
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.09
    -output
    0.08
    /output
    0.08
    물ìĿĦ
    0.08
     output
    0.08
    ted
    0.07
     OUTPUT
    0.07
    _Tis
    0.07
    output
    0.07
    /result
    0.07
    Activations Density 0.055%

    No Known Activations