© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129628
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or scenarios that indicate uncertainty or prerequisites

    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
    otyping
    -0.07
    ilion
    -0.06
     Fo
    -0.06
    οÏħÏģγ
    -0.06
    alars
    -0.06
    zek
    -0.06
    óg
    -0.06
    ecess
    -0.06
    nik
    -0.06
    swick
    -0.06
    POSITIVE LOGITS
     accompagn
    0.07
     underlying
    0.07
     accompany
    0.06
    uppe
    0.06
    rie
    0.06
    none
    0.06
    ÅĻi
    0.06
    kaar
    0.06
    resse
    0.06
     %#
    0.06
    Activations Density 0.013%

    No Known Activations