© 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. 117742
    Prev
    Next
    INDEX
    Explanations

    terms related to oceanic and atmospheric processes

    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
    abis
    -0.06
    adders
    -0.06
    ulk
    -0.06
    ulet
    -0.06
    emma
    -0.06
    obb
    -0.06
    ivr
    -0.06
    ordova
    -0.06
    ebo
    -0.06
    cky
    -0.05
    POSITIVE LOGITS
     wind
    0.10
     winds
    0.10
     breeze
    0.09
     circulation
    0.09
    wind
    0.08
     Wind
    0.08
    flows
    0.08
     Winds
    0.08
    vection
    0.08
    風
    0.08
    Activations Density 0.093%

    No Known Activations