© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and related values associated with technology and systems

    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
    há
    -0.07
    osten
    -0.07
    lect
    -0.07
    npos
    -0.06
    ity
    -0.06
    bang
    -0.06
    647
    -0.06
    atives
    -0.06
    izen
    -0.06
    ithub
    -0.06
    POSITIVE LOGITS
    Conv
    0.07
    ound
    0.07
    uddy
    0.06
    ieur
    0.06
    LEX
    0.06
     Conv
    0.06
    oup
    0.06
     Reserved
    0.06
    imos
    0.06
    cheid
    0.06
    Activations Density 0.037%

    No Known Activations