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. 44019
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to data and mathematical expressions

    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
    íĸ¥
    -0.06
    udy
    -0.06
     اÙĦعÙĦÙħ
    -0.06
     Vend
    -0.06
     Sonic
    -0.06
     jurors
    -0.06
    ivas
    -0.06
     Firmware
    -0.06
     Thermal
    -0.06
     Apprentice
    -0.06
    POSITIVE LOGITS
     humanitarian
    0.14
     relief
    0.11
     donors
    0.11
     reconstruction
    0.11
     donor
    0.11
     Relief
    0.10
     assistance
    0.09
     Reconstruction
    0.09
     Kosovo
    0.09
     Disaster
    0.09
    Activations Density 0.004%

    No Known Activations