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. 43833
    Prev
    Next
    INDEX
    Explanations

    specialized mathematical terms and symbols

    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
    inson
    -0.06
     Karn
    -0.06
    PLAY
    -0.06
     Carn
    -0.06
    ยาย
    -0.06
    ÅĻaz
    -0.06
    Zoom
    -0.06
     concert
    -0.06
    tet
    -0.06
    PROTO
    -0.06
    POSITIVE LOGITS
    upo
    0.08
     Olymp
    0.08
     Wet
    0.07
     Olympic
    0.07
     USSR
    0.07
    awl
    0.07
     Olympia
    0.07
    kg
    0.07
    _weights
    0.07
     Ud
    0.07
    Activations Density 0.003%

    No Known Activations