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. 43891
    Prev
    Next
    INDEX
    Explanations

    events related to space launches and missions

    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
    .createFrom
    -0.07
    gal
    -0.06
    ÏģοÏįν
    -0.06
    742
    -0.06
     ali
    -0.06
    BufferSize
    -0.06
     Truman
    -0.06
     alien
    -0.06
    ystone
    -0.06
    нин
    -0.06
    POSITIVE LOGITS
     loft
    0.14
     lif
    0.11
     Loft
    0.10
     carrying
    0.09
     lift
    0.09
     ferry
    0.09
     blasted
    0.09
     Lif
    0.09
     lifted
    0.09
     blasting
    0.09
    Activations Density 0.010%

    No Known Activations