© 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. 120766
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to software and data management

    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
     tuy
    -0.07
    UPI
    -0.06
    olis
    -0.06
    ÙĬÙĩ
    -0.06
    onis
    -0.06
     <$>
    -0.06
    quam
    -0.06
    brig
    -0.06
    keh
    -0.06
    ÑĢеÑī
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.16
    then
    0.15
     then
    0.15
     THEN
    0.13
    ï¼ĮçĦ¶åIJİ
    0.13
    _then
    0.11
     rá»ĵi
    0.11
    Then
    0.11
    	then
    0.11
     Then
    0.11
    Activations Density 0.075%

    No Known Activations