© 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. 120983
    Prev
    Next
    INDEX
    Explanations

    references to customer feedback and buying experiences

    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
    .to
    -0.06
    ynes
    -0.06
    pressed
    -0.06
    -de
    -0.06
     Mor
    -0.05
    -
    -0.05
     Som
    -0.05
     Rum
    -0.05
    avy
    -0.05
     Hum
    -0.05
    POSITIVE LOGITS
    Sizer
    0.08
    inka
    0.07
    .ul
    0.07
    USTER
    0.07
    .Debugf
    0.07
    514
    0.07
    chw
    0.07
    RLF
    0.07
    939
    0.07
    ::__
    0.07
    Activations Density 0.001%

    No Known Activations