© 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. 127493
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "the" and other specific article usage in text

    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
    olec
    -0.08
    ůj
    -0.07
    licas
    -0.07
     eens
    -0.07
    ONG
    -0.07
    ong
    -0.07
    å¦ĸ
    -0.07
    è°±
    -0.07
    à¹Ģà¸ľ
    -0.07
    GLuint
    -0.07
    POSITIVE LOGITS
     should
    0.06
    rim
    0.06
    oretical
    0.05
    -Key
    0.05
    686
    0.05
     Ston
    0.05
     Bucc
    0.05
    æ°ij
    0.05
     Ange
    0.05
    obi
    0.05
    Activations Density 0.006%

    No Known Activations