© 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. 42311
    Prev
    Next
    INDEX
    Explanations

    The presence 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
     world
    -0.07
    -0.07
     :
    -0.06
     old
    -0.06
     certain
    -0.06
     divert
    -0.06
    ↵
    -0.06
     (
    -0.06
     nothing
    -0.06
     Brady
    -0.05
    POSITIVE LOGITS
    ëĺIJ
    0.10
    avaÅŁ
    0.10
    ì´Ŀ
    0.09
    ãģªãģĬ
    0.09
    Sharper
    0.09
     ayrıca
    0.09
    AlmostEqual
    0.09
     ì´Ŀ
    0.08
    ινÏĮ
    0.08
    елик
    0.08
    Activations Density 0.048%

    No Known Activations