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. 44204
    Prev
    Next
    INDEX
    Explanations

    special characters and non-standard symbols within the text

    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
    ango
    -0.07
     Diablo
    -0.06
     Buenos
    -0.06
    ulp
    -0.06
     Avalanche
    -0.06
     Boulder
    -0.06
     Alpine
    -0.06
     Antarctica
    -0.06
     Canyon
    -0.06
     Antarctic
    -0.06
    POSITIVE LOGITS
     township
    0.10
     Mg
    0.09
     Th
    0.09
     Township
    0.09
     Org
    0.08
     Md
    0.08
     Tv
    0.07
     Naw
    0.07
     naw
    0.07
     Ny
    0.07
    Activations Density 0.003%

    No Known Activations