© 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. 42355
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the" in different 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
    nock
    -0.08
    erte
    -0.08
     Mitar
    -0.07
    ayah
    -0.07
    ntag
    -0.06
    truncate
    -0.06
    ardash
    -0.06
     Harding
    -0.06
    /devices
    -0.06
    okoj
    -0.06
    POSITIVE LOGITS
    å®ŀ
    0.06
    vl
    0.06
    mia
    0.06
    _abstract
    0.06
    ema
    0.06
    duce
    0.06
     Reeves
    0.06
    andez
    0.06
    oble
    0.06
    rez
    0.06
    Activations Density 0.047%

    No Known Activations