© 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. 130728
    Prev
    Next
    INDEX
    Explanations

    references to RSS feeds and related technology concepts

    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
    fos
    -0.07
    ạnh
    -0.07
    eness
    -0.06
     ÙĨÙģ
    -0.06
    PDF
    -0.06
     searchable
    -0.06
    loth
    -0.06
     Vimeo
    -0.06
     sal
    -0.06
    eno
    -0.06
    POSITIVE LOGITS
     feed
    0.13
     feeds
    0.12
     Feed
    0.11
     RSS
    0.11
    -feed
    0.10
    .feed
    0.10
    Feed
    0.10
    feed
    0.10
     subscribe
    0.09
    RSS
    0.09
    Activations Density 0.024%

    No Known Activations