© 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. 4708
    Prev
    Next
    INDEX
    Explanations

    temporal adverbs and phrases indicating time or sequence

    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
    issen
    -0.08
    bstract
    -0.07
    /Common
    -0.07
    åº
    -0.07
    Uploaded
    -0.07
     suy
    -0.06
     Fallen
    -0.06
    alis
    -0.06
     collided
    -0.06
     getApp
    -0.06
    POSITIVE LOGITS
     another
    0.09
     Giang
    0.07
     sources
    0.07
    another
    0.07
    imid
    0.06
    maf
    0.06
     two
    0.06
    pus
    0.06
    rema
    0.06
    igy
    0.06
    Activations Density 0.024%

    No Known Activations