© 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. 57076
    Prev
    Next
    INDEX
    Explanations

    health-related observations regarding aquatic ecosystems

    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
    chsel
    -0.06
     Held
    -0.06
    .functions
    -0.06
     refin
    -0.06
     neh
    -0.06
    å¬
    -0.06
     Vo
    -0.06
     Raven
    -0.06
    asin
    -0.06
    çon
    -0.06
    POSITIVE LOGITS
     appearances
    0.08
     signs
    0.08
     appearance
    0.07
    ông
    0.07
    æ¯
    0.07
     appeared
    0.07
     indications
    0.06
     visibly
    0.06
    Cpp
    0.06
    indrome
    0.06
    Activations Density 0.038%

    No Known Activations