© 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. 121131
    Prev
    Next
    INDEX
    Explanations

    references to the Internet and web-related topics

    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
    pong
    -0.07
    chi
    -0.06
    grid
    -0.06
    طار
    -0.06
    ierarchical
    -0.06
    çīĻ
    -0.06
    rypt
    -0.06
    asco
    -0.06
    alim
    -0.06
    mu
    -0.06
    POSITIVE LOGITS
    wb
    0.07
    Cast
    0.06
    رÙĪت
    0.06
    WB
    0.06
    apg
    0.06
    olumn
    0.06
     OVERRIDE
    0.06
    olor
    0.06
    rost
    0.06
    ignon
    0.06
    Activations Density 0.005%

    No Known Activations