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. 43968
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with dates or quantities

    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
    ngth
    -0.06
    ccess
    -0.06
    roud
    -0.06
     hours
    -0.06
    zee
    -0.06
     intellig
    -0.05
    owitz
    -0.05
     sincerely
    -0.05
     either
    -0.05
    cks
    -0.05
    POSITIVE LOGITS
    ÙĪÛĮس
    0.08
    ạnh
    0.07
    utzer
    0.07
    958
    0.07
    μεÏģ
    0.07
    åĶ
    0.07
    .Unity
    0.07
    illis
    0.07
     hvis
    0.06
    ÙĪÙĬس
    0.06
    Activations Density 0.014%

    No Known Activations