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. 43942
    Prev
    Next
    INDEX
    Explanations

    HTML and XML markup tags

    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
     Th
    -0.08
    ola
    -0.06
     Te
    -0.06
    iolet
    -0.06
     Tau
    -0.06
    Ïģη
    -0.06
     Tur
    -0.06
     Ha
    -0.06
     Tea
    -0.06
    -T
    -0.06
    POSITIVE LOGITS
    th
    0.14
    <th
    0.12
    thead
    0.10
    yh
    0.10
    thr
    0.10
    thon
    0.09
    ths
    0.09
     trh
    0.09
    	th
    0.09
     columnHeader
    0.09
    Activations Density 0.005%

    No Known Activations