© 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. 17-LLAMASCOPE-RES-131K
    11. 83793
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" in various 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
     chalk
    -0.06
    ish
    -0.06
    ib
    -0.06
    itere
    -0.06
     Umb
    -0.06
    file
    -0.06
    gart
    -0.06
     Brooks
    -0.06
    875
    -0.06
    raci
    -0.06
    POSITIVE LOGITS
    ys
    0.07
    ieres
    0.07
    oodle
    0.06
    ÑĮко
    0.06
    CLU
    0.06
    ÙĪÙģÙĬ
    0.06
    ypsum
    0.06
     allegedly
    0.06
    umper
    0.06
    æĶ
    0.06
    Activations Density 0.027%

    No Known Activations