© 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. 15537
    Prev
    Next
    INDEX
    Explanations

    phrases related to distribution and logistics

    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
    eurs
    -0.07
    UserCode
    -0.07
    BACKGROUND
    -0.06
    uiten
    -0.06
    ÂłkW
    -0.06
    ascar
    -0.06
     /*!↵
    -0.06
    ósito
    -0.06
    ÃŃl
    -0.06
    hits
    -0.06
    POSITIVE LOGITS
    haf
    0.07
    LastError
    0.07
    748
    0.07
     Truy
    0.06
    è¬
    0.06
    ahat
    0.06
    ائد
    0.06
    allel
    0.06
    ired
    0.06
    513
    0.06
    Activations Density 0.062%

    No Known Activations