© 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. 118775
    Prev
    Next
    INDEX
    Explanations

    references to due dates and deadlines

    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
    ÑĩеÑģ
    -0.07
     Omega
    -0.07
    emes
    -0.07
    halt
    -0.06
    anan
    -0.06
    avou
    -0.06
     slow
    -0.06
    ERV
    -0.06
    eview
    -0.06
     stopwatch
    -0.06
    POSITIVE LOGITS
     deadline
    0.08
    oted
    0.08
    piry
    0.07
     stated
    0.07
     allotted
    0.07
     pros
    0.06
    toPromise
    0.06
    deadline
    0.06
    hin
    0.06
     window
    0.06
    Activations Density 0.012%

    No Known Activations