© 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 EvalsExportsAPI 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. 126527
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables used in mathematical equations

    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
     hear
    -0.09
    elter
    -0.08
    igel
    -0.08
     heard
    -0.08
     hearing
    -0.07
     Hearing
    -0.07
     Hear
    -0.07
     knowing
    -0.07
     hears
    -0.07
    agate
    -0.07
    POSITIVE LOGITS
    797
    0.06
    393
    0.06
    nej
    0.06
    743
    0.06
    £
    0.06
    Ïĥη
    0.06
    inus
    0.06
    rias
    0.06
    nal
    0.06
    ione
    0.06
    Activations Density 0.181%

    No Known Activations