© 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. 88401
    Prev
    Next
    INDEX
    Explanations

    software applications and related tools

    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
    ä¹ĭä¸Ģ
    -0.07
    SenderId
    -0.06
    Calculator
    -0.06
    /buttons
    -0.06
    ogn
    -0.06
    Printing
    -0.06
    ancell
    -0.06
    .provider
    -0.06
     Britann
    -0.06
    ameda
    -0.06
    POSITIVE LOGITS
    .exe
    0.09
    AES
    0.08
    olley
    0.08
    ico
    0.07
    etag
    0.07
    -ng
    0.07
    abin
    0.07
    iros
    0.07
    ®
    0.06
    ÙĬÙĥÙĬ
    0.06
    Activations Density 0.021%

    No Known Activations