© 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. 117516
    Prev
    Next
    INDEX
    Explanations

    phrases related to website functionality and user experience

    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
     TÆ°
    -0.07
    ime
    -0.07
    ched
    -0.07
    atz
    -0.07
     branch
    -0.07
    ilk
    -0.07
    ãģ®æĸ¹
    -0.06
    branches
    -0.06
     ãĥį
    -0.06
    ucken
    -0.06
    POSITIVE LOGITS
    147
    0.07
     tÃŃnh
    0.06
    functions
    0.06
     functions
    0.06
    ishments
    0.06
    325
    0.06
    397
    0.06
     Funktion
    0.06
     subtotal
    0.06
     ple
    0.06
    Activations Density 0.000%

    No Known Activations