© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75610
    Prev
    Next
    INDEX
    Explanations

    references to urgency or promptness

    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
    zing
    -0.07
    ailable
    -0.07
    ting
    -0.07
    ytt
    -0.07
    eting
    -0.07
    shake
    -0.06
    mare
    -0.06
    cob
    -0.06
    .Options
    -0.06
     Spare
    -0.06
    POSITIVE LOGITS
     rather
    0.09
     versus
    0.08
     vs
    0.07
     Rather
    0.07
     sooner
    0.07
    adow
    0.07
    rather
    0.07
     than
    0.07
    anging
    0.07
    -than
    0.07
    Activations Density 0.002%

    No Known Activations