© 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. 72476
    Prev
    Next
    INDEX
    Explanations

    topics related to ecosystems and environmental science

    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
    EMU
    -0.08
    educt
    -0.08
    ajes
    -0.07
    emen
    -0.07
    γη
    -0.06
    boru
    -0.06
    ovacÃŃ
    -0.06
    oday
    -0.06
    RAND
    -0.06
    erap
    -0.06
    POSITIVE LOGITS
     Haz
    0.07
    NaN
    0.06
     Microsystems
    0.06
    ensch
    0.06
     ÙĩÙĨÚ¯
    0.06
     Henri
    0.06
    cache
    0.06
     Ways
    0.05
    andan
    0.05
     Specialist
    0.05
    Activations Density 0.095%

    No Known Activations