© 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. 108288
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

    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
    BarButtonItem
    -0.07
    (DialogInterface
    -0.07
    ãģ¾ãģ¾
    -0.07
    âĨIJ
    -0.07
     forIndexPath
    -0.07
    ibil
    -0.07
    esh
    -0.07
     راÛĮ
    -0.06
    Assignable
    -0.06
    .DEFINE
    -0.06
    POSITIVE LOGITS
    :↵
    0.13
    :
    0.12
     :↵
    0.09
    :↵↵
    0.09
    ï¼ļ↵
    0.07
    :č↵
    0.07
    nam
    0.07
    :<
    0.07
    :"↵
    0.06
     namely
    0.06
    Activations Density 0.064%

    No Known Activations