© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103419
    Prev
    Next
    INDEX
    Explanations

    the word "substantial" and its variants

    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
    ess
    -0.07
    ican
    -0.07
    ов
    -0.07
    scape
    -0.07
    ew
    -0.07
    -за
    -0.07
    ogenous
    -0.07
    asper
    -0.07
    -0.06
    zens
    -0.06
    POSITIVE LOGITS
    alist
    0.09
    ively
    0.09
    ity
    0.08
    mente
    0.08
    ilty
    0.08
     <!--[
    0.07
    dehyde
    0.07
    ÄĽt
    0.07
    ly
    0.07
    257
    0.06
    Activations Density 0.005%

    No Known Activations