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. 22-LLAMASCOPE-RES-131K
    6. 5632
    Prev
    Next
    INDEX
    Explanations

    terms related to structured organizations and roles within them

    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
     {{--<
    -0.09
    ÙĪÙĩ
    -0.08
    @js
    -0.08
    plorer
    -0.08
    [js
    -0.08
     تصÙħ
    -0.07
    baÅŁ
    -0.07
    straints
    -0.07
    anzi
    -0.07
    jist
    -0.07
    POSITIVE LOGITS
     both
    0.13
     everywhere
    0.12
     various
    0.12
     several
    0.12
     respectively
    0.11
    åĪĨåĪ«
    0.11
     such
    0.10
    :
    0.09
     wherever
    0.09
     numerous
    0.09
    Activations Density 0.069%

    No Known Activations