© 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. 118885
    Prev
    Next
    INDEX
    Explanations

    dates and numerical data related to events

    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
    	Copyright
    -0.07
    ãĥ«ãĥī
    -0.06
    UDA
    -0.06
     analy
    -0.06
    yses
    -0.06
    allen
    -0.06
     Ludwig
    -0.06
    dba
    -0.06
    tridge
    -0.06
    aly
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥł
    0.07
     GObject
    0.07
     Ä°li
    0.07
    à¥įतव
    0.07
    Įĵ
    0.07
    ADX
    0.07
    arro
    0.07
    ibold
    0.07
    Toolkit
    0.07
    ož
    0.06
    Activations Density 0.010%

    No Known Activations