© 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. 60465
    Prev
    Next
    INDEX
    Explanations

    instances of significant actions or 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
     compatibility
    -0.08
    compatible
    -0.07
    compat
    -0.07
    fits
    -0.07
     fitting
    -0.07
    osti
    -0.07
    Äħd
    -0.07
    ILLA
    -0.07
    tical
    -0.07
     fits
    -0.07
    POSITIVE LOGITS
     datings
    0.08
     dating
    0.07
    dating
    0.06
     Raq
    0.06
     taper
    0.06
    ä¸Ī
    0.06
    odate
    0.05
     SetProperty
    0.05
    ừng
    0.05
    ÃŃc
    0.05
    Activations Density 0.063%

    No Known Activations