© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38407
    Prev
    Next
    INDEX
    Explanations

    phrases related to market fluctuations and investor sentiment

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ÃĹ↵↵
    -0.07
    infeld
    -0.07
    utin
    -0.07
    adla
    -0.06
    ì§ĵ
    -0.06
    EDA
    -0.06
    orp
    -0.06
    -pad
    -0.06
    515
    -0.06
    declspec
    -0.06
    POSITIVE LOGITS
     Russell
    0.08
     our
    0.07
    amo
    0.07
    dna
    0.06
     ourselves
    0.06
     returns
    0.06
    isin
    0.06
    hy
    0.06
    bow
    0.06
    achine
    0.06
    Activations Density 0.004%

    No Known Activations