© 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. 92790
    Prev
    Next
    INDEX
    Explanations

    references to the word "a" and its variations, emphasizing articles and their significance in the context

    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
    лади
    -0.07
    _OCCURRED
    -0.06
    ertia
    -0.06
    ekk
    -0.06
    atten
    -0.06
    _prefs
    -0.06
    èĪ¬
    -0.06
    OUNDS
    -0.06
    itte
    -0.06
    252
    -0.06
    POSITIVE LOGITS
     sake
    0.12
     purposes
    0.11
     reasons
    0.10
     instance
    0.09
    agers
    0.09
    aging
    0.09
     granted
    0.08
    /by
    0.08
     Granted
    0.08
     sure
    0.08
    Activations Density 0.046%

    No Known Activations