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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104065
    Prev
    Next
    INDEX
    Explanations

    terms related to energy production and consumption

    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
     worldwide
    -0.06
     Dest
    -0.05
     insert
    -0.05
     ton
    -0.05
     sweetheart
    -0.05
     order
    -0.05
     amen
    -0.05
     instantaneous
    -0.05
     tail
    -0.05
     ment
    -0.05
    POSITIVE LOGITS
    energy
    0.08
     energy
    0.08
    èĮĤ
    0.08
     seedu
    0.08
    LOPT
    0.08
     Tradable
    0.07
    xima
    0.07
     chatte
    0.07
    mite
    0.07
    arness
    0.07
    Activations Density 0.016%

    No Known Activations