© 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. 82914
    Prev
    Next
    INDEX
    Explanations

    instances of the definite article "the" 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
    irs
    -0.06
    .pageX
    -0.06
     Beckham
    -0.06
    efeller
    -0.06
     Bands
    -0.05
    ãĤ¹ãĥĿ
    -0.05
     MPS
    -0.05
    _inds
    -0.05
    bud
    -0.05
    Qui
    -0.05
    POSITIVE LOGITS
    ritel
    0.08
    amedi
    0.07
    ummer
    0.07
    Integral
    0.07
    raud
    0.07
    unct
    0.06
    éric
    0.06
    celed
    0.06
    htar
    0.06
     Ludwig
    0.06
    Activations Density 0.045%

    No Known Activations