© 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. 9-LLAMASCOPE-RES-131K
    11. 95663
    Prev
    Next
    INDEX
    Explanations

    JavaScript and jQuery function calls and event handling 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
    aldi
    -0.08
    730
    -0.07
    ott
    -0.07
    cod
    -0.06
    736
    -0.06
    eg
    -0.06
    heimer
    -0.06
    ersh
    -0.06
    erc
    -0.06
    encing
    -0.06
    POSITIVE LOGITS
     Wings
    0.06
     Locker
    0.06
    _LANG
    0.06
    erman
    0.06
     rencont
    0.06
    apis
    0.06
     Ensemble
    0.06
     عÙĪ
    0.06
    Ease
    0.06
     Foundations
    0.06
    Activations Density 0.002%

    No Known Activations