© 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. 93061
    Prev
    Next
    INDEX
    Explanations

    data related to stock market metrics and financial performance indicators

    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
    ossip
    -0.06
    lug
    -0.06
     Bounty
    -0.06
    itud
    -0.06
    iks
    -0.05
    äºĭåĭĻ
    -0.05
    à¹Ģ
    -0.05
     sm
    -0.05
    roduce
    -0.05
     Pulse
    -0.05
    POSITIVE LOGITS
    DCF
    0.08
    _fwd
    0.07
     Nas
    0.07
     valuation
    0.07
    -valu
    0.07
    czy
    0.07
    alte
    0.06
    value
    0.06
    nez
    0.06
     ratios
    0.06
    Activations Density 0.008%

    No Known Activations