© 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. 130766
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "just" in various contexts, indicating simplicity or exclusivity

    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
     Sokol
    -0.08
    884
    -0.07
    .LayoutStyle
    -0.07
     instead
    -0.07
    alles
    -0.07
    002
    -0.06
     nowhere
    -0.06
    arella
    -0.06
     none
    -0.06
    ì°¬
    -0.06
    POSITIVE LOGITS
     merely
    0.11
     mere
    0.09
    mere
    0.08
    åıªæĺ¯
    0.07
    odate
    0.07
     juste
    0.06
    Disposed
    0.06
     INCIDENT
    0.06
     blindly
    0.06
    jac
    0.06
    Activations Density 0.020%

    No Known Activations