Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125767
    Prev
    Next
    INDEX
    Explanations

    references to quantities or amounts

    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
    orra
    -0.08
    åĿª
    -0.07
    loo
    -0.07
    наÑĢ
    -0.06
    otle
    -0.06
    iÄį
    -0.06
    .googleapis
    -0.06
    aign
    -0.06
     Naz
    -0.06
    uppe
    -0.06
    POSITIVE LOGITS
     of
    0.10
    åħ¶ä¸Ń
    0.10
     parte
    0.10
     aspects
    0.09
     these
    0.09
    ones
    0.08
     aspect
    0.08
     cá»§a
    0.08
     portion
    0.08
     part
    0.07
    Activations Density 0.044%

    No Known Activations