© 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. 17-LLAMASCOPE-RES-131K
    11. 93871
    Prev
    Next
    INDEX
    Explanations

    terms related to sustainability and environmental impact

    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
    unas
    -0.07
    anas
    -0.07
    warts
    -0.07
    oÅĽci
    -0.07
     подÑģ
    -0.06
    ardi
    -0.06
    Äįer
    -0.06
    andle
    -0.06
     reusable
    -0.06
     zug
    -0.06
    POSITIVE LOGITS
     costly
    0.09
     traditional
    0.08
     resort
    0.08
     otherwise
    0.08
    erville
    0.08
     expensive
    0.08
     conventional
    0.08
     later
    0.08
     Traditional
    0.07
     altogether
    0.07
    Activations Density 0.030%

    No Known Activations