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. 43872
    Prev
    Next
    INDEX
    Explanations

    high frequency occurrences of content that conveys importance or significance

    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
     last
    -0.07
    (last
    -0.07
     first
    -0.07
     previously
    -0.07
    last
    -0.07
    (first
    -0.07
     today
    -0.06
     earlier
    -0.06
    074
    -0.06
     докÑĥм
    -0.06
    POSITIVE LOGITS
    Next
    0.21
     Next
    0.17
    _next
    0.14
    .Next
    0.14
    _NEXT
    0.12
     NEXT
    0.12
    -next
    0.12
     next
    0.11
    next
    0.10
    .next
    0.10
    Activations Density 0.005%

    No Known Activations