© 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. 75197
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical terms and 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
    æĸĹ
    -0.06
     Gordon
    -0.06
     ÑĢаÐ
    -0.06
    _callable
    -0.06
    627
    -0.06
    ogui
    -0.06
    Portal
    -0.06
    ä¹¾
    -0.06
    rak
    -0.06
    ilter
    -0.06
    POSITIVE LOGITS
    (:,
    0.10
     columns
    0.09
     column
    0.09
    ivec
    0.08
    -column
    0.08
     Columns
    0.08
    column
    0.07
    /column
    0.07
    ettel
    0.07
    loud
    0.07
    Activations Density 0.394%

    No Known Activations