© 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. 39565
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical notations or structures

    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
    kil
    -0.06
    oons
    -0.06
    ething
    -0.06
    amento
    -0.06
     Inches
    -0.06
    Äįku
    -0.06
    vil
    -0.06
    æŀľ
    -0.06
    ecess
    -0.06
    iazza
    -0.06
    POSITIVE LOGITS
    nard
    0.07
    <Func
    0.07
    è¦
    0.06
    ract
    0.06
    ayne
    0.06
     Henderson
    0.06
     hex
    0.06
    fully
    0.06
    شد
    0.06
    drv
    0.06
    Activations Density 0.000%

    No Known Activations