© 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. 94903
    Prev
    Next
    INDEX
    Explanations

    terminology related to technical or operational procedures, particularly in the context of space missions

    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
    ombo
    -0.08
    idot
    -0.07
    ignal
    -0.06
    ampion
    -0.06
    uguay
    -0.06
    phylum
    -0.06
    rika
    -0.06
    acco
    -0.06
    WebHost
    -0.06
    ristol
    -0.06
    POSITIVE LOGITS
     mission
    0.07
     Energ
    0.06
     Agricult
    0.06
     Mission
    0.06
     UNITY
    0.06
    -rated
    0.06
    arta
    0.06
    aste
    0.06
    éré
    0.06
    .GetEnumerator
    0.06
    Activations Density 0.009%

    No Known Activations