© 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. 15-LLAMASCOPE-RES-131K
    11. 90374
    Prev
    Next
    INDEX
    Explanations

    references to medical studies or clinical trial data

    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
    187
    -0.07
    870
    -0.06
    ern
    -0.06
    icus
    -0.05
    188
    -0.05
    748
    -0.05
    ette
    -0.05
    ettes
    -0.05
     partial
    -0.05
     Vern
    -0.05
    POSITIVE LOGITS
    azon
    0.08
     ÙħÛĮÙĦادÛĮ
    0.08
    orex
    0.08
    è§
    0.08
    .normalize
    0.07
    ormal
    0.07
    itta
    0.07
    ç´¹
    0.07
     Intermediate
    0.07
    ivy
    0.07
    Activations Density 0.011%

    No Known Activations