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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15938
    Prev
    Next
    INDEX
    Explanations

    references to specific dates or events in a timely context

    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
    妮
    -0.07
    èĽĩ
    -0.07
    _LED
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    _stdio
    -0.06
     Mezi
    -0.06
    озна
    -0.06
    assi
    -0.06
     addCriterion
    -0.06
     Leban
    -0.06
    POSITIVE LOGITS
     announcement
    0.07
    announcement
    0.07
     announcements
    0.06
    leh
    0.06
     release
    0.06
    ÑĨип
    0.06
    eÄį
    0.06
     announce
    0.06
     I
    0.05
     launch
    0.05
    Activations Density 0.008%

    No Known Activations