© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125078
    Prev
    Next
    INDEX
    Explanations

    variations of the word "as" 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
     ÙħÚ©
    -0.10
    оÑĤÑĮ
    -0.09
    οÏįÏĤ
    -0.08
    ç»ıèIJ¥
    -0.08
    .scalablytyped
    -0.08
    ãĥĥãĥĦ
    -0.08
     isize
    -0.08
    ë§ī
    -0.08
    uby
    -0.08
    Installer
    -0.08
    POSITIVE LOGITS
     happened
    0.10
     happens
    0.10
     done
    0.09
     happen
    0.08
     most
    0.08
     happening
    0.07
    oci
    0.06
     recent
    0.06
     some
    0.06
     happ
    0.06
    Activations Density 0.025%

    No Known Activations