© 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. 9-LLAMASCOPE-RES-131K
    11. 97966
    Prev
    Next
    INDEX
    Explanations

    technical programming elements and code snippets

    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
    jas
    -0.06
    ellas
    -0.06
    .baidu
    -0.06
    ÑĤал
    -0.06
     Newman
    -0.06
    olia
    -0.06
     Deborah
    -0.06
    izoph
    -0.06
     Sao
    -0.06
    acco
    -0.05
    POSITIVE LOGITS
    TreeWidgetItem
    0.07
     $?
    0.07
    ê¶Į
    0.07
    utzer
    0.06
    alama
    0.06
    ustin
    0.06
    AndWait
    0.06
    DTD
    0.06
    kick
    0.06
     Eck
    0.06
    Activations Density 0.145%

    No Known Activations