© 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. 39416
    Prev
    Next
    INDEX
    Explanations

    references to specific instances or subjects

    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
    ypes
    -0.07
     same
    -0.06
    ertype
    -0.06
     Disqus
    -0.06
     overt
    -0.06
    inic
    -0.06
    enet
    -0.06
    uels
    -0.06
    Ïħμ
    -0.06
     imposed
    -0.05
    POSITIVE LOGITS
     ones
    0.10
    egra
    0.07
    بار
    0.07
    ¶Į
    0.07
     "?"
    0.07
     Ones
    0.07
    Axes
    0.07
    usra
    0.07
    557
    0.06
    ullan
    0.06
    Activations Density 0.010%

    No Known Activations