© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84504
    Prev
    Next
    INDEX
    Explanations

    key historical events related to space exploration

    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
    ofs
    -0.06
     reconstruction
    -0.06
     zel
    -0.06
    ifu
    -0.06
     carn
    -0.06
     forEach
    -0.06
     kav
    -0.06
    culo
    -0.06
     region
    -0.05
     Ventura
    -0.05
    POSITIVE LOGITS
    196
    0.09
    _launch
    0.08
     Soviets
    0.07
    inus
    0.07
    Ä©
    0.07
     Ð¡Ð¡Ð¡Ðł
    0.07
     Soviet
    0.07
    tach
    0.07
    ÅĻiv
    0.07
    оке
    0.07
    Activations Density 0.006%

    No Known Activations