© 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. 87493
    Prev
    Next
    INDEX
    Explanations

    the occurrence of definite articles

    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
     scene
    -0.06
    GetProperty
    -0.06
     past
    -0.06
     teil
    -0.06
    urma
    -0.06
     ahead
    -0.06
     Scene
    -0.06
    :
    -0.06
     creative
    -0.05
    701
    -0.05
    POSITIVE LOGITS
    jen
    0.08
    portun
    0.07
     corre
    0.07
    ÏĪε
    0.07
    ugo
    0.07
     nIndex
    0.07
    aoke
    0.07
     corresponding
    0.07
    _Utils
    0.07
    .snp
    0.07
    Activations Density 0.071%

    No Known Activations