© 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. 125284
    Prev
    Next
    INDEX
    Explanations

    themes related to health, governance, and cultural discussions

    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
     and
    -0.10
     и
    -0.08
     vÃł
    -0.07
     ìŀĪê³ł
    -0.07
     ÈĻi
    -0.07
    åĴĮ
    -0.07
    and
    -0.07
    ضÛĮ
    -0.07
     és
    -0.06
    icast
    -0.06
    POSITIVE LOGITS
     alike
    0.13
     íķ¨ê»ĺ
    0.07
    ä¸Ģèµ·
    0.07
     thereof
    0.07
     serta
    0.06
    .Factory
    0.06
    UGIN
    0.06
    pus
    0.06
    931
    0.06
     respectively
    0.06
    Activations Density 0.048%

    No Known Activations