© 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. 15-LLAMASCOPE-RES-131K
    11. 89351
    Prev
    Next
    INDEX
    Explanations

    terms related to data sheets and embodied energy in the context of circular economy

    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
    èĩ¨
    -0.06
    Ī¬
    -0.06
    amedi
    -0.05
     advance
    -0.05
    åłĤ
    -0.05
    teÅŁ
    -0.05
     Billy
    -0.05
    _STAT
    -0.05
    åĻ¨
    -0.05
    ==>
    -0.05
    POSITIVE LOGITS
    elta
    0.08
    orary
    0.07
    strup
    0.07
    eltas
    0.07
     calcul
    0.07
    oeff
    0.07
    rlen
    0.07
    odium
    0.07
    ellen
    0.06
    shal
    0.06
    Activations Density 0.005%

    No Known Activations