© 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 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. 17-LLAMASCOPE-RES-131K
    11. 125769
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    umper
    -0.08
    Streamer
    -0.07
    serrat
    -0.07
     sayıda
    -0.07
    ea
    -0.07
    bang
    -0.07
    dad
    -0.06
    ebilecek
    -0.06
    egade
    -0.06
    USH
    -0.06
    POSITIVE LOGITS
    .k
    0.09
    oret
    0.09
    orz
    0.07
    atre
    0.07
     cui
    0.07
    oretical
    0.07
     only
    0.07
     embodiment
    0.07
    ãģĤãĤĭ
    0.06
    omain
    0.06
    Activations Density 0.025%

    No Known Activations