© 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. 15-LLAMASCOPE-RES-131K
    11. 88378
    Prev
    Next
    INDEX
    Explanations

    exclamations and special characters in mathematical contexts

    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
    chw
    -0.07
    amos
    -0.07
    ynes
    -0.07
    idel
    -0.07
     Irving
    -0.07
    tic
    -0.07
     chung
    -0.07
    ledon
    -0.07
    uncia
    -0.07
    agne
    -0.06
    POSITIVE LOGITS
     compl
    0.06
     proper
    0.06
     ever
    0.06
    FIXME
    0.06
     Bieber
    0.05
     Hava
    0.05
    fcn
    0.05
     SC
    0.05
    yth
    0.05
     Ellen
    0.05
    Activations Density 0.003%

    No Known Activations