© 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. 82754
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary supplements and health regulations

    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
     outdoor
    -0.06
     styled
    -0.06
     Gore
    -0.06
    reeNode
    -0.06
    lust
    -0.06
     infected
    -0.06
     Wire
    -0.06
    sty
    -0.06
     Tobacco
    -0.06
    edla
    -0.06
    POSITIVE LOGITS
     Bilg
    0.08
     capsules
    0.07
     Mega
    0.07
     Sesso
    0.07
     NSK
    0.07
    å¯
    0.07
     PIO
    0.07
     Schwarz
    0.07
     PHY
    0.07
    mega
    0.07
    Activations Density 0.078%

    No Known Activations