Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5371
    Prev
    Next
    INDEX
    Explanations

    references to companies or entities involved in production or distribution

    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
    util
    -0.06
     Bros
    -0.05
    IBM
    -0.05
    amax
    -0.05
    formatted
    -0.05
    ute
    -0.05
    ãĤ¡
    -0.05
    Reusable
    -0.05
    (return
    -0.05
    igr
    -0.05
    POSITIVE LOGITS
     release
    0.10
     Release
    0.10
     releases
    0.09
    .release
    0.09
     released
    0.09
    -release
    0.09
    release
    0.08
    Release
    0.08
     Official
    0.08
    _release
    0.08
    Activations Density 0.001%

    No Known Activations