© 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. 128862
    Prev
    Next
    INDEX
    Explanations

    the word "was" 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
    ocht
    -0.07
    æĦ
    -0.07
    uko
    -0.06
    innie
    -0.06
    ussen
    -0.06
     Gamb
    -0.06
    olog
    -0.06
    ë°į
    -0.06
    ullet
    -0.06
    oplayer
    -0.06
    POSITIVE LOGITS
     recently
    0.10
    nt
    0.07
     Recently
    0.07
    Recently
    0.07
     personally
    0.06
     originally
    0.06
     last
    0.06
    407
    0.06
     previously
    0.06
     trunc
    0.06
    Activations Density 0.021%

    No Known Activations