© 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. 87569
    Prev
    Next
    INDEX
    Explanations

    the word "just" in various contexts

    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
    بس
    -0.07
    kir
    -0.07
    dden
    -0.06
    кин
    -0.06
    ALIGN
    -0.06
     Maver
    -0.06
    pool
    -0.06
    cir
    -0.06
    uire
    -0.06
    lsi
    -0.06
    POSITIVE LOGITS
    ifying
    0.07
    ifice
    0.06
    ifies
    0.06
    opia
    0.06
    ifications
    0.06
     moments
    0.06
    jos
    0.06
    ifiers
    0.06
    tml
    0.06
    UnderTest
    0.06
    Activations Density 0.016%

    No Known Activations