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. 43965
    Prev
    Next
    INDEX
    Explanations

    symbols and elements related to mathematical expressions or functions

    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
    .Toolkit
    -0.08
    CallCheck
    -0.07
    afone
    -0.07
    ogl
    -0.07
     Tar
    -0.07
    \CMS
    -0.06
     èĩªåĬ¨çĶŁæĪIJ
    -0.06
    erli
    -0.06
    Tar
    -0.06
    _lng
    -0.06
    POSITIVE LOGITS
     vest
    0.15
     awards
    0.15
     award
    0.13
     grant
    0.13
     Awards
    0.13
     grants
    0.13
     employee
    0.12
     Award
    0.12
     options
    0.12
     vested
    0.12
    Activations Density 0.006%

    No Known Activations