© 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 EvalsExportsinterp-engineNEWAPI 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. 79244
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms and tenses

    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
    âĢ¦↵
    -0.07
    iene
    -0.06
    302
    -0.06
    ..↵
    -0.06
     âĢ¦↵
    -0.06
    hs
    -0.06
    quartered
    -0.06
    ...↵
    -0.06
    hra
    -0.05
     [âĢ¦]↵
    -0.05
    POSITIVE LOGITS
    Interop
    0.09
    ----------------------------------------------------------------------↵
    0.09
    лаÑģÑĤи
    0.09
     зави
    0.09
     jich
    0.08
    лиÑĪ
    0.08
    /pub
    0.08
    ì§ĢëıĦ
    0.08
    specs
    0.08
    ÙĬدا
    0.08
    Activations Density 0.068%

    No Known Activations