© 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. 18672
    Prev
    Next
    INDEX
    Explanations

    phrases expressing knowledge and understanding of expectations

    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
    _SF
    -0.07
    ãĥ¬ãĥ¼
    -0.07
    tember
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    WISE
    -0.06
    ãģıãģ¨
    -0.06
    alion
    -0.06
    APPER
    -0.06
    ÏĢον
    -0.06
    parator
    -0.06
    POSITIVE LOGITS
     knew
    0.16
     know
    0.15
     knows
    0.14
     known
    0.14
    know
    0.14
    known
    0.14
     KNOW
    0.13
    çŁ¥éģĵ
    0.13
     knowing
    0.13
     Know
    0.13
    Activations Density 0.038%

    No Known Activations