© 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. 93946
    Prev
    Next
    INDEX
    Explanations

    terms related to financial performance metrics and company assessments

    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
     calculator
    -0.06
    irut
    -0.06
    лаз
    -0.06
    adero
    -0.06
    ặt
    -0.06
    جاÙĨ
    -0.05
    >::
    -0.05
    repair
    -0.05
    awy
    -0.05
     hos
    -0.05
    POSITIVE LOGITS
    erval
    0.07
    roma
    0.07
    женÑĮ
    0.07
    )frame
    0.07
    heck
    0.07
    (&(
    0.07
    Ä©
    0.06
    abus
    0.06
    etes
    0.06
    readystatechange
    0.06
    Activations Density 0.004%

    No Known Activations