© 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. 837
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with health and wellness

    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
     Ton
    -0.07
    Ton
    -0.06
    upo
    -0.06
    enza
    -0.06
    icana
    -0.06
    олоÑģ
    -0.06
    راÙĤ
    -0.06
    ÙĪÙĤÙģ
    -0.06
     Sky
    -0.06
    _Syntax
    -0.06
    POSITIVE LOGITS
     versions
    0.10
     version
    0.09
     edition
    0.09
    /version
    0.09
     editions
    0.08
     VERSION
    0.08
    çīĪ
    0.08
    çīĪæľ¬
    0.07
     versión
    0.07
    316
    0.07
    Activations Density 0.033%

    No Known Activations