© 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. 39487
    Prev
    Next
    INDEX
    Explanations

    the letter 'o' 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
     intros
    -0.06
    ÃŃme
    -0.06
    ë£Į
    -0.06
    umas
    -0.06
     classics
    -0.06
    eydi
    -0.06
    .echo
    -0.06
    zer
    -0.06
    aydı
    -0.06
    âĢİ
    -0.06
    POSITIVE LOGITS
    idden
    0.07
    acre
    0.07
    až
    0.07
    ãĥĬãĥ¼
    0.06
    æĺ¯ä¸į
    0.06
    abin
    0.06
    INCLUDED
    0.06
    aunch
    0.06
    upert
    0.06
    MEA
    0.06
    Activations Density 0.000%

    No Known Activations