© 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. 77221
    Prev
    Next
    INDEX
    Explanations

    references to dates and locations in conference presentations

    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
    ettel
    -0.08
    ilden
    -0.06
    amik
    -0.06
     carriage
    -0.06
    uler
    -0.06
     Ops
    -0.06
    èIJ¥
    -0.06
    astreet
    -0.06
    ONSE
    -0.06
    idge
    -0.06
    POSITIVE LOGITS
    held
    0.07
     Kramer
    0.07
     held
    0.07
    -held
    0.07
    cale
    0.06
    ansi
    0.06
    variants
    0.06
    portion
    0.06
    portun
    0.06
    caled
    0.06
    Activations Density 0.004%

    No Known Activations