© 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. 86033
    Prev
    Next
    INDEX
    Explanations

    phrases expressing future actions or predictions

    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
    æ¿
    -0.09
    atsu
    -0.08
    uchs
    -0.08
    adle
    -0.07
    ssi
    -0.07
    ì°©
    -0.07
    ansson
    -0.07
     Hatch
    -0.07
    oreach
    -0.07
    yal
    -0.07
    POSITIVE LOGITS
     attempt
    0.07
     hoping
    0.07
     Snowden
    0.07
     attempts
    0.06
     test
    0.06
     hopes
    0.06
     try
    0.06
    ardon
    0.06
     tough
    0.06
    kee
    0.06
    Activations Density 0.032%

    No Known Activations