© 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. 55535
    Prev
    Next
    INDEX
    Explanations

    mentions of major technology events or product launches

    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
     Becker
    -0.07
     Mam
    -0.06
    978
    -0.06
     recommended
    -0.05
     drag
    -0.05
    /browse
    -0.05
     concentration
    -0.05
    ts
    -0.05
     uns
    -0.05
     rem
    -0.05
    POSITIVE LOGITS
     preview
    0.12
    -preview
    0.12
     previews
    0.10
     leaks
    0.10
    preview
    0.10
     leaked
    0.10
    _preview
    0.10
    Leaks
    0.10
    announcement
    0.10
     Preview
    0.09
    Activations Density 0.207%

    No Known Activations