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. 43867
    Prev
    Next
    INDEX
    Explanations

    terms related to aircraft and their specifications

    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
    hazi
    -0.08
    afen
    -0.08
    alars
    -0.07
    arnation
    -0.07
    vince
    -0.07
    ège
    -0.07
    ajaran
    -0.07
    CJK
    -0.07
    amage
    -0.07
    olars
    -0.07
    POSITIVE LOGITS
     McDon
    0.10
     Douglas
    0.10
     Mirage
    0.10
     Mess
    0.10
     Haw
    0.09
     Conv
    0.09
     Suk
    0.09
     Blackburn
    0.09
     Lockheed
    0.09
     Fair
    0.09
    Activations Density 0.035%

    No Known Activations