© 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. 54658
    Prev
    Next
    INDEX
    Explanations

    numerical values and related formatting in the text

    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
    ihat
    -0.06
     personalised
    -0.06
    Enlarge
    -0.06
    -doc
    -0.06
    wich
    -0.06
    quis
    -0.06
     Ãľy
    -0.06
    ayla
    -0.06
    aar
    -0.06
    .receive
    -0.06
    POSITIVE LOGITS
     hãy
    0.09
     don
    0.09
     try
    0.09
     use
    0.08
    Don
    0.08
     pick
    0.07
     make
    0.07
    Go
    0.07
    use
    0.07
    Ñģлед
    0.07
    Activations Density 0.059%

    No Known Activations