© 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. 107621
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and related phrases emphasizing its frequency and significance in the text

    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
    ilde
    -0.08
    égor
    -0.07
    oter
    -0.07
    stru
    -0.07
    eren
    -0.06
    otify
    -0.06
    ongan
    -0.06
    abb
    -0.06
    .export
    -0.06
    ajan
    -0.06
    POSITIVE LOGITS
    BOSE
    0.07
    GINE
    0.07
    Ìģ
    0.06
     Stateless
    0.06
    tone
    0.06
    HING
    0.06
    ì»
    0.06
    ãģĵ
    0.06
    Ĺ
    0.06
    иÑģÑĮ
    0.06
    Activations Density 0.161%

    No Known Activations