© 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 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. 17-LLAMASCOPE-RES-131K
    11. 85602
    Prev
    Next
    INDEX
    Explanations

    financial metrics related to company 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
    umpt
    -0.08
    apia
    -0.08
    plib
    -0.07
    SSIP
    -0.07
    hots
    -0.07
    оÑĤÑĮ
    -0.07
    itol
    -0.07
    yclopedia
    -0.07
    обÑī
    -0.07
    erval
    -0.07
    POSITIVE LOGITS
     Fore
    0.07
     fore
    0.07
    0.06
     mas
    0.06
     mah
    0.06
     cr
    0.06
     one
    0.06
     ideally
    0.06
     exped
    0.05
    oran
    0.05
    Activations Density 0.021%

    No Known Activations