© 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. 17948
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement, analysis, and physical properties in scientific contexts

    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
    elin
    -0.07
    :async
    -0.07
    essler
    -0.07
    /stretch
    -0.07
    deÅŁ
    -0.07
    rescia
    -0.07
    ê·¹
    -0.07
    ÙĪاز
    -0.06
     Gene
    -0.06
    webtoken
    -0.06
    POSITIVE LOGITS
     value
    0.07
    edly
    0.07
    ALLY
    0.07
    /core
    0.07
    ná
    0.06
    ingly
    0.06
    -wise
    0.06
    åĢ¤
    0.06
    mente
    0.06
    toPromise
    0.06
    Activations Density 0.077%

    No Known Activations