© 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 EvalsExportsinterp-engineNEWAPI 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. 108257
    Prev
    Next
    INDEX
    Explanations

    phrases that involve research and studies

    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
     onto
    -0.09
    ामन
    -0.07
    okt
    -0.07
    udi
    -0.07
    reib
    -0.07
    ook
    -0.07
    ensed
    -0.07
    avirus
    -0.07
    olest
    -0.07
    ensen
    -0.06
    POSITIVE LOGITS
     separately
    0.07
     aspects
    0.07
     aspect
    0.07
     whether
    0.06
     alongside
    0.06
     separate
    0.06
    ate
    0.06
     further
    0.06
    ume
    0.06
    sing
    0.06
    Activations Density 0.031%

    No Known Activations