© 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. 54521
    Prev
    Next
    INDEX
    Explanations

    economic and business concepts related to industry performance and organization

    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
    ìĿ´ê³ł
    -0.10
     ìŀĪê³ł
    -0.10
    ëIJĺê³ł
    -0.08
    )&&(
    -0.07
     totiž
    -0.07
     and
    -0.07
     ìķĬê³ł
    -0.07
    @s
    -0.07
    ì§Ģê³ł
    -0.07
    )&&
    -0.07
    POSITIVE LOGITS
     alike
    0.10
     serta
    0.09
     respectively
    0.09
     etc
    0.09
    ersen
    0.08
     ÑĤоÑīо
    0.08
    etc
    0.08
     ëĵ±ìĿĺ
    0.08
     Äijá»ģu
    0.08
     gibi
    0.07
    Activations Density 0.463%

    No Known Activations