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. 43381
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    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
    olley
    -0.07
    /Register
    -0.07
    afari
    -0.07
    رÙģØª
    -0.07
     رÙĪØ§ÙĨ
    -0.07
    eÅŁ
    -0.06
    ALCHEMY
    -0.06
    åľŃ
    -0.06
     Jaguar
    -0.06
     PyErr
    -0.06
    POSITIVE LOGITS
     Te
    0.12
     Tradition
    0.10
     Russian
    0.10
     village
    0.09
     tradition
    0.09
     Russians
    0.09
    Russian
    0.08
     milk
    0.08
     Milk
    0.08
     Y
    0.08
    Activations Density 0.004%

    No Known Activations