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. 43686
    Prev
    Next
    INDEX
    Explanations

    references to specific concepts or elements within a shared context

    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
     disparate
    -0.08
     requisite
    -0.08
     decidedly
    -0.07
     ostensibly
    -0.07
     unwitting
    -0.06
     burgeoning
    -0.06
     fled
    -0.06
     whence
    -0.06
    ahl
    -0.06
    aign
    -0.06
    POSITIVE LOGITS
    ese
    0.12
     mentioned
    0.12
     âĢŀ
    0.12
     nowadays
    0.11
     whole
    0.11
     splitted
    0.10
     serie
    0.10
    oric
    0.10
     standart
    0.10
     lenght
    0.10
    Activations Density 0.185%

    No Known Activations