© 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. 82877
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to notable figures

    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
    ós
    -0.07
    æ´²
    -0.07
    ouse
    -0.07
    aries
    -0.06
    OfString
    -0.06
    striction
    -0.06
    sar
    -0.06
    หาย
    -0.06
    ening
    -0.06
    igu
    -0.06
    POSITIVE LOGITS
     latter
    0.07
    ess
    0.07
    brush
    0.07
    -serif
    0.07
    ernals
    0.07
    essim
    0.07
    lings
    0.06
    ius
    0.06
    ird
    0.06
    own
    0.06
    Activations Density 0.025%

    No Known Activations