© 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. 93079
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to set theory and graph theory

    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
     Erect
    -0.06
    oran
    -0.06
    avan
    -0.06
     Corey
    -0.06
    ottes
    -0.06
    idlo
    -0.06
    ensa
    -0.06
    _Api
    -0.05
     shop
    -0.05
     ITE
    -0.05
    POSITIVE LOGITS
    สำหร
    0.08
    compass
    0.07
    (_)
    0.07
     for
    0.07
    _FOREACH
    0.07
    ateral
    0.07
     reserved
    0.07
     pentru
    0.06
    zym
    0.06
    pra
    0.06
    Activations Density 0.103%

    No Known Activations