© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 87025
    Prev
    Next
    INDEX
    Explanations

    references to scientific topics and terminologies, particularly in the context of health

    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
    γγ
    -0.07
    acades
    -0.07
    mel
    -0.07
    	Il
    -0.06
    ï¼¾
    -0.06
    λÏī
    -0.06
    ])**
    -0.06
    èĩ¨
    -0.06
    lags
    -0.06
     Penalty
    -0.06
    POSITIVE LOGITS
    kee
    0.07
    heel
    0.07
     see
    0.06
    -purple
    0.06
    -One
    0.06
     overview
    0.06
    ð
    0.06
     See
    0.06
    rist
    0.06
     defined
    0.06
    Activations Density 0.004%

    No Known Activations