Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11524
    Prev
    Next
    INDEX
    Explanations

    references to sports events and their scheduling details

    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
    igung
    -0.06
    oli
    -0.06
    æ°¸ä¹ħ
    -0.06
    atoria
    -0.06
    ÅĻ
    -0.06
    ency
    -0.05
    گرÛĮ
    -0.05
    ominator
    -0.05
     zat
    -0.05
    ustr
    -0.05
    POSITIVE LOGITS
     televised
    0.13
     televis
    0.12
     TV
    0.12
     television
    0.11
     broadcast
    0.11
     NBC
    0.10
    -TV
    0.10
     ESPN
    0.10
    TV
    0.10
     airs
    0.10
    Activations Density 0.035%

    No Known Activations