© 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. 62720
    Prev
    Next
    INDEX
    Explanations

    references to external entities and third-party influences

    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
     McCart
    -0.07
    uthor
    -0.06
    ยว
    -0.06
    egrity
    -0.06
     mennes
    -0.06
     conc
    -0.06
     genu
    -0.06
    .baomidou
    -0.06
    uards
    -0.05
     macOS
    -0.05
    POSITIVE LOGITS
    eck
    0.08
    Enlarge
    0.08
    üre
    0.07
    ãĥ¼ãĥł
    0.07
     rej
    0.07
    볨
    0.07
     schle
    0.06
     æ¸
    0.06
    Helvetica
    0.06
    751
    0.06
    Activations Density 0.000%

    No Known Activations