© 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. 54703
    Prev
    Next
    INDEX
    Explanations

    instances of the word "just"

    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
    ictionary
    -0.07
    cxx
    -0.06
    eniable
    -0.06
    alink
    -0.06
    ár
    -0.06
    ignum
    -0.06
    ruc
    -0.06
    ród
    -0.06
     drinking
    -0.06
    889
    -0.06
    POSITIVE LOGITS
     finished
    0.09
     recently
    0.07
     finishing
    0.07
     finish
    0.07
    emek
    0.07
     RELEASE
    0.07
     Klaus
    0.06
    woke
    0.06
    .finished
    0.06
    å®Į
    0.06
    Activations Density 0.010%

    No Known Activations