© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38569
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various forms and 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
    ï¸
    -0.08
    Required
    -0.08
     required
    -0.08
    _required
    -0.08
     need
    -0.08
     Required
    -0.07
    ÏīÏĤ
    -0.07
    лагод
    -0.07
    chwitz
    -0.07
     Require
    -0.07
    POSITIVE LOGITS
     обÑıзаÑĤелÑĮно
    0.09
    æīįèĥ½
    0.07
     careful
    0.07
    n
    0.07
     somehow
    0.06
    ur
    0.06
     carefully
    0.06
    aph
    0.06
    agram
    0.06
    ÙĨ
    0.06
    Activations Density 0.032%

    No Known Activations