© 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. 4858
    Prev
    Next
    INDEX
    Explanations

    financial terms related to accounting measures

    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
    ensi
    -0.08
    urat
    -0.08
    icari
    -0.08
    ByExample
    -0.08
    ัà¸Ĺ
    -0.07
    sealed
    -0.07
    견
    -0.07
    lycer
    -0.07
    icus
    -0.07
    batim
    -0.07
    POSITIVE LOGITS
     net
    0.07
    immel
    0.06
     rent
    0.06
     Net
    0.06
     sadd
    0.06
     nets
    0.06
     ort
    0.06
    ted
    0.06
    NET
    0.05
     dil
    0.05
    Activations Density 0.003%

    No Known Activations