© 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. 54995
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ultimate."

    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
    sm
    -0.08
    æļ®
    -0.08
    rint
    -0.07
    atori
    -0.07
    ALES
    -0.07
    room
    -0.07
    íĵ¨
    -0.07
    ÑĥÑĩа
    -0.07
    amba
    -0.07
    shal
    -0.07
    POSITIVE LOGITS
    istically
    0.08
    imate
    0.07
    bert
    0.07
    uros
    0.06
    imately
    0.06
    оÑģÑĮ
    0.06
    isky
    0.06
    istic
    0.06
    ices
    0.06
    inate
    0.06
    Activations Density 0.005%

    No Known Activations