© 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. 73168
    Prev
    Next
    INDEX
    Explanations

    terms associated with artistic and digital processes

    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
    els
    -0.08
    IRE
    -0.07
    anas
    -0.07
    tures
    -0.07
    orra
    -0.07
    ãģĭãĤīãģ®
    -0.07
    urent
    -0.07
    sets
    -0.07
    leÅŁik
    -0.07
    aira
    -0.06
    POSITIVE LOGITS
    istically
    0.09
    ically
    0.09
    antically
    0.08
    ologically
    0.08
    elize
    0.08
    ifies
    0.07
    lessly
    0.07
    astically
    0.07
    izes
    0.07
    ursively
    0.07
    Activations Density 0.165%

    No Known Activations