© 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. 9-LLAMASCOPE-RES-131K
    11. 97478
    Prev
    Next
    INDEX
    Explanations

    references to different types of oils and their applications

    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
    ÑĤеÑĢн
    -0.06
    ervlet
    -0.06
    .ready
    -0.06
    Disclosure
    -0.06
     Ñģка
    -0.06
    FORE
    -0.06
    Mate
    -0.05
     Yen
    -0.05
    acon
    -0.05
    siz
    -0.05
    POSITIVE LOGITS
    å¥Ķ
    0.07
    abama
    0.07
    ts
    0.07
    asio
    0.07
    ãģĨãģ¡
    0.07
    iginal
    0.06
    portun
    0.06
    naÄįenÃŃ
    0.06
    ensively
    0.06
     ComVisible
    0.06
    Activations Density 0.009%

    No Known Activations