© 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. 108270
    Prev
    Next
    INDEX
    Explanations

    mathematical references, particularly theorems, lemmas, and definitions

    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
    onga
    -0.07
    lobber
    -0.06
     SUBSTITUTE
    -0.06
    ç¸
    -0.06
     Cay
    -0.06
    mass
    -0.06
     cel
    -0.06
     cast
    -0.05
    ">*</
    -0.05
    argas
    -0.05
    POSITIVE LOGITS
    ideo
    0.07
    ãĥ©ãĥĥãĤ¯
    0.07
     velit
    0.06
    orida
    0.06
    lette
    0.06
    stant
    0.06
     TMPro
    0.06
    uns
    0.06
    ecko
    0.06
     Prot
    0.06
    Activations Density 0.003%

    No Known Activations