© 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 EvalsExportsinterp-engineNEWAPI 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. 1779
    Prev
    Next
    INDEX
    Explanations

    expressions related to expectations, hopes, and anticipations about outcomes

    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
    ccd
    -0.07
    dration
    -0.07
    ĵ
    -0.06
    irl
    -0.06
    egas
    -0.06
    ashi
    -0.06
    803
    -0.06
    alty
    -0.06
     Emp
    -0.06
    eso
    -0.06
    POSITIVE LOGITS
     originally
    0.08
     initially
    0.07
     Originally
    0.07
     Stevenson
    0.07
     inicial
    0.07
    Originally
    0.06
     Initially
    0.06
    Ùĩ
    0.06
    initial
    0.06
     initial
    0.06
    Activations Density 0.011%

    No Known Activations