© 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. 69504
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to significant events, community initiatives, and actions

    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
    اÙģت
    -0.07
    erin
    -0.07
    rowable
    -0.06
    alian
    -0.06
    urgeon
    -0.06
    ÑĢÑĥ
    -0.06
     cds
    -0.06
     ax
    -0.06
     such
    -0.06
    atables
    -0.06
    POSITIVE LOGITS
    -ci
    0.07
     particular
    0.07
     guy
    0.07
    alone
    0.07
    ÙĦسÙĦ
    0.07
    venge
    0.06
    nost
    0.06
    иÑĤелÑĮнÑĭй
    0.06
    eur
    0.06
    -fontawesome
    0.06
    Activations Density 0.393%

    No Known Activations