© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75701
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and cooling systems

    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
    opo
    -0.06
    riet
    -0.06
    .Prot
    -0.06
    irma
    -0.06
    llx
    -0.06
    slaught
    -0.06
     ration
    -0.06
    ÅĻet
    -0.06
    combe
    -0.06
    emek
    -0.06
    POSITIVE LOGITS
     heat
    0.08
     exchanging
    0.08
     Heat
    0.07
     ex
    0.07
     contacting
    0.07
    Heat
    0.07
    heat
    0.07
    ex
    0.07
    _exchange
    0.07
    èĴ
    0.07
    Activations Density 0.027%

    No Known Activations