© 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. 123442
    Prev
    Next
    INDEX
    Explanations

    instances of "need" or "to" in context, particularly in relation to obligations and requirements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    еÑĤа
    -0.07
    iap
    -0.07
     treff
    -0.07
    ayd
    -0.07
    ereo
    -0.07
    ä¸ĢåĪĩ
    -0.06
    iants
    -0.06
    aversable
    -0.06
    illin
    -0.06
    .nc
    -0.06
    POSITIVE LOGITS
     multiple
    0.09
     several
    0.08
     additional
    0.07
     resort
    0.07
     some
    0.07
    veral
    0.07
    multiple
    0.07
     extra
    0.06
     slightly
    0.06
     assistance
    0.06
    Activations Density 0.024%

    No Known Activations