© 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. 79783
    Prev
    Next
    INDEX
    Explanations

    conditional statements and future predictions

    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
     když
    -0.07
    ÏĥÏĦα
    -0.07
    WithURL
    -0.07
    ãģłãĤĪ
    -0.07
     ByteArrayOutputStream
    -0.07
    assing
    -0.07
     didnt
    -0.07
    .scalablytyped
    -0.06
    APPER
    -0.06
    894
    -0.06
    POSITIVE LOGITS
     will
    0.11
     then
    0.10
    will
    0.10
     THEN
    0.09
     would
    0.09
    çļĦè¯Ŀ
    0.09
     würde
    0.09
     sẽ
    0.08
    å°±ä¼ļ
    0.08
    then
    0.08
    Activations Density 0.031%

    No Known Activations