© 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. 126901
    Prev
    Next
    INDEX
    Explanations

    terms related to Olympic sports and championships

    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
    mess
    -0.07
    tha
    -0.07
    Translation
    -0.06
    upert
    -0.06
    edReader
    -0.06
    á»Ŀ
    -0.06
    agna
    -0.06
     desar
    -0.06
    oder
    -0.06
    fat
    -0.06
    POSITIVE LOGITS
    iti
    0.06
    ottage
    0.06
    icc
    0.06
     Duty
    0.06
     brides
    0.06
    ummings
    0.06
    RefCount
    0.06
    ë³µ
    0.06
    æķ·
    0.06
    893
    0.06
    Activations Density 0.006%

    No Known Activations