© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98889
    Prev
    Next
    INDEX
    Explanations

    indefinite articles and their associated phrases

    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
    isi
    -0.07
    ãģıãģł
    -0.06
     acc
    -0.06
    ici
    -0.06
    اساÙĨ
    -0.06
    áŁĴáŀ
    -0.06
    ÑĢан
    -0.06
     typ
    -0.06
    ains
    -0.06
     Eisen
    -0.06
    POSITIVE LOGITS
    UpInside
    0.07
    \uff
    0.07
    compact
    0.06
     Thomson
    0.06
    enor
    0.06
    adir
    0.06
    contri
    0.06
    esta
    0.06
     Ngá»įc
    0.06
    uxtap
    0.06
    Activations Density 0.007%

    No Known Activations