© 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. 17-LLAMASCOPE-RES-131K
    11. 18537
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" and similar indefinite 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
    ury
    -0.07
    orem
    -0.07
    ãĥ¥
    -0.07
    elsey
    -0.07
    æĻ¨
    -0.07
    ories
    -0.06
    Ãłng
    -0.06
    ãģĵãĤį
    -0.06
    endum
    -0.06
    rof
    -0.06
    POSITIVE LOGITS
     dozen
    0.14
     hundred
    0.08
     thousand
    0.07
     деÑģÑıÑĤ
    0.07
     decade
    0.06
    UMB
    0.06
     handful
    0.06
    DownList
    0.06
     million
    0.06
     Rec
    0.06
    Activations Density 0.012%

    No Known Activations