© 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. 84235
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "timely" and its variations, indicating a focus on promptness and punctuality

    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
    èĩ
    -0.07
    alian
    -0.06
    sta
    -0.06
    ç²
    -0.06
    izen
    -0.06
    901
    -0.06
    elf
    -0.06
     entire
    -0.06
    allo
    -0.06
    sel
    -0.06
    POSITIVE LOGITS
    posables
    0.09
    othy
    0.09
     manner
    0.09
    ness
    0.08
    tics
    0.08
    ร
    0.07
    NESS
    0.07
    itous
    0.07
    ypress
    0.07
    åĪ»
    0.07
    Activations Density 0.005%

    No Known Activations