© 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. 79175
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of uncertainty

    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
     fool
    -0.07
     TAR
    -0.06
    emachine
    -0.06
    urat
    -0.06
     Rosenstein
    -0.06
    æ¯ķ
    -0.06
    YC
    -0.06
    foy
    -0.06
    olet
    -0.06
    inel
    -0.06
    POSITIVE LOGITS
    berra
    0.08
    uga
    0.08
    odes
    0.07
    bjerg
    0.07
     lav
    0.07
    ÙĪاء
    0.07
     even
    0.06
     ever
    0.06
     Traditional
    0.06
     ØŃتÙī
    0.06
    Activations Density 0.029%

    No Known Activations