© 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. 15-LLAMASCOPE-RES-131K
    11. 90661
    Prev
    Next
    INDEX
    Explanations

    references to specific days and timelines

    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
    apper
    -0.08
     jo
    -0.07
    ẫ
    -0.07
    atcher
    -0.07
    zew
    -0.06
     Budd
    -0.06
    ilim
    -0.06
     eventually
    -0.06
     progression
    -0.06
    plotlib
    -0.06
    POSITIVE LOGITS
    Effective
    0.06
    £
    0.06
     Technical
    0.06
     Howell
    0.06
    ambi
    0.06
     effective
    0.06
    Technical
    0.06
     itibaren
    0.06
    401
    0.06
     Everywhere
    0.06
    Activations Density 0.021%

    No Known Activations