© 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. 18426
    Prev
    Next
    INDEX
    Explanations

    words indicating quantification or frequency

    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
    mere
    -0.06
    ãĤ¤ãĤº
    -0.06
    emark
    -0.06
    pper
    -0.06
     stuff
    -0.06
    ady
    -0.06
    884
    -0.06
    za
    -0.06
    sville
    -0.06
    seys
    -0.06
    POSITIVE LOGITS
     IDictionary
    0.07
    olland
    0.07
    research
    0.07
    erspective
    0.07
     authors
    0.06
    ình
    0.06
    é»
    0.06
    AWN
    0.06
    ilit
    0.06
     scholars
    0.06
    Activations Density 0.038%

    No Known Activations