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

    Neuronpedia

    Jacobian LensNEW
    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. 130573
    Prev
    Next
    INDEX
    Explanations

    references to community organizations and 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
    ÙĪÙĨد
    -0.07
    urt
    -0.06
    uba
    -0.06
     wast
    -0.06
    Äĵ
    -0.06
    λη
    -0.05
     indul
    -0.05
     ph
    -0.05
    ovny
    -0.05
     revolution
    -0.05
    POSITIVE LOGITS
     events
    0.14
    events
    0.12
     Events
    0.12
     eventos
    0.11
     activities
    0.11
    Events
    0.10
    /events
    0.10
     event
    0.10
     activity
    0.10
    _events
    0.09
    Activations Density 0.043%

    No Known Activations