© 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. 17810
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations, particularly related to functions, equations, and variables

    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
    áÄį
    -0.07
    дем
    -0.07
    owell
    -0.07
    окÑĢем
    -0.07
    loo
    -0.07
    ulls
    -0.07
    ecome
    -0.07
    oyo
    -0.07
    .Pixel
    -0.07
    ÑĢид
    -0.06
    POSITIVE LOGITS
    weg
    0.06
    0.06
    oman
    0.06
     Sunder
    0.06
    pNet
    0.06
    622
    0.06
    RefPtr
    0.06
     Rubin
    0.06
    cis
    0.06
    ldr
    0.06
    Activations Density 0.744%

    No Known Activations