© 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. 17-LLAMASCOPE-RES-131K
    11. 106027
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and symbols

    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
    vale
    -0.06
    ogh
    -0.06
    FU
    -0.06
    aled
    -0.06
    Ø·Ùģ
    -0.06
     ãĥ«
    -0.06
    зÑĮ
    -0.06
     Searches
    -0.06
     accelerator
    -0.05
    apers
    -0.05
    POSITIVE LOGITS
    reflection
    0.08
     reflection
    0.08
     Reflection
    0.07
    Reflection
    0.07
    arness
    0.07
     fres
    0.07
     Fres
    0.07
     Green
    0.07
    óc
    0.07
     reflected
    0.07
    Activations Density 0.075%

    No Known Activations