© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61533
    Prev
    Next
    INDEX
    Explanations

    specific financial metrics or statistics related to stock performance

    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
    gewater
    -0.07
    547
    -0.06
    inq
    -0.06
     Mand
    -0.06
     aid
    -0.05
    éł¼
    -0.05
    ambi
    -0.05
    Mounted
    -0.05
     supplements
    -0.05
     Marsh
    -0.05
    POSITIVE LOGITS
    orb
    0.08
    csi
    0.07
    ndl
    0.07
    erin
    0.07
    labs
    0.07
    ÏĦÏİ
    0.07
    bottom
    0.07
    rán
    0.07
    änn
    0.07
     lows
    0.07
    Activations Density 0.006%

    No Known Activations