© 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 EvalsExportsAPI 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. 130482
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting in text

    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
     THEN
    -0.09
    THEN
    -0.08
     سپس
    -0.08
     then
    -0.08
    then
    -0.07
    Then
    -0.07
     âĹĭ
    -0.07
    urdu
    -0.07
     Then
    -0.07
     رÙĪÛĮ
    -0.07
    POSITIVE LOGITS
     indeed
    0.11
     Indeed
    0.11
    Indeed
    0.10
     previous
    0.08
     already
    0.08
     earlier
    0.07
     totiž
    0.07
     Already
    0.07
    inde
    0.07
     especially
    0.07
    Activations Density 0.025%

    No Known Activations