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. 44053
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical operators used in equations

    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
    piler
    -0.07
    thora
    -0.06
     PUBLIC
    -0.06
     jadx
    -0.06
    undy
    -0.06
    atcher
    -0.06
     Public
    -0.06
    ppo
    -0.06
     Loop
    -0.05
    arsi
    -0.05
    POSITIVE LOGITS
     trait
    0.16
     implicit
    0.15
     object
    0.15
     sealed
    0.14
    implicit
    0.14
    trait
    0.13
    object
    0.13
     def
    0.13
    sealed
    0.13
     final
    0.11
    Activations Density 0.004%

    No Known Activations