© 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. 107870
    Prev
    Next
    INDEX
    Explanations

    references to investment performance and stock market activity

    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
    ivr
    -0.07
    ENSITY
    -0.07
    اذ
    -0.07
    agini
    -0.07
    .codes
    -0.07
    chg
    -0.07
    arez
    -0.07
    à¥Ĥद
    -0.06
    Collapsed
    -0.06
    NIL
    -0.06
    POSITIVE LOGITS
     mot
    0.06
     Fool
    0.06
     Henderson
    0.06
     Frost
    0.06
     Brett
    0.06
    ãĤ¤ãĥ¤
    0.06
    mast
    0.05
     Mot
    0.05
    ul
    0.05
     Slim
    0.05
    Activations Density 0.007%

    No Known Activations