© 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. 60948
    Prev
    Next
    INDEX
    Explanations

    Java class loader-related terms and references

    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
    utow
    -0.09
    ovit
    -0.07
     arac
    -0.07
     wet
    -0.07
    afort
    -0.07
     ëĭ¤ìļ´ë°Ľê¸°
    -0.07
    égor
    -0.07
    ="__
    -0.06
    Ùģ
    -0.06
    	Copyright
    -0.06
    POSITIVE LOGITS
    zig
    0.07
    ened
    0.07
    melon
    0.06
    lessly
    0.06
    orie
    0.06
    Solver
    0.06
    UNG
    0.06
    اÙģتÙĩ
    0.06
    oe
    0.06
    /release
    0.06
    Activations Density 0.000%

    No Known Activations