© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 73414
    Prev
    Next
    INDEX
    Explanations

    the word "via" associated with sources or attributions 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
    oret
    -0.08
     opposite
    -0.06
    kara
    -0.06
    visible
    -0.06
     Tweets
    -0.06
    kou
    -0.06
    è¶
    -0.06
    iem
    -0.06
    visa
    -0.06
     carr
    -0.06
    POSITIVE LOGITS
    uraa
    0.07
    ero
    0.07
    /commons
    0.07
    PLIED
    0.06
    ãĥ³ãĥĸ
    0.06
    AllWindows
    0.06
    BOTTOM
    0.06
     dụ
    0.06
    oba
    0.06
     %[
    0.06
    Activations Density 0.002%

    No Known Activations