© 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. 106491
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvements in performance and efficiency

    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
    á»ĩ
    -0.07
    é¾Ħ
    -0.07
    encias
    -0.07
    adata
    -0.06
    ÑĸлÑĸ
    -0.06
    aging
    -0.06
    oram
    -0.06
    errer
    -0.06
    inputEmail
    -0.06
    çħ§
    -0.06
    POSITIVE LOGITS
     Twin
    0.07
     lungs
    0.07
     rev
    0.07
     Garrett
    0.07
     respir
    0.06
    ÄIJT
    0.06
     Oxygen
    0.06
     Jen
    0.06
    Headers
    0.06
    ÎĮ
    0.06
    Activations Density 0.000%

    No Known Activations