© 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. 105641
    Prev
    Next
    INDEX
    Explanations

    character counts or punctuation density

    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
    InputDialog
    -0.08
    ĶĦ
    -0.08
    xfd
    -0.08
    nees
    -0.08
    ĶåĽŀ
    -0.07
     '#{
    -0.07
    illet
    -0.07
    į¼
    -0.07
    rese
    -0.07
    ecd
    -0.07
    POSITIVE LOGITS
     "
    0.13
     «
    0.11
     "(
    0.08
    ="
    0.08
     """
    0.08
    0.08
    "I
    0.08
     “
    0.07
    "It
    0.07
    "That
    0.07
    Activations Density 0.020%

    No Known Activations