© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84035
    Prev
    Next
    INDEX
    Explanations

    educational content related to Excel training and tutorials

    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
    -quote
    -0.07
     Kı
    -0.07
    коп
    -0.06
    /tiny
    -0.06
    ãĥ³ãĥIJ
    -0.06
    ijken
    -0.06
    .sell
    -0.06
    atter
    -0.06
    جÙĩ
    -0.06
    laÅŁ
    -0.06
    POSITIVE LOGITS
    -module
    0.08
    -session
    0.07
     Anatomy
    0.07
     Introduction
    0.07
     Session
    0.07
     introduction
    0.07
     session
    0.07
     intro
    0.06
    module
    0.06
    atomy
    0.06
    Activations Density 0.010%

    No Known Activations