© 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. 63137
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and necessity

    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
    reso
    -0.07
    ãģķãĤī
    -0.07
     dikke
    -0.07
     stripe
    -0.07
    _ud
    -0.07
    enci
    -0.07
    件
    -0.07
    æģµ
    -0.07
    mdat
    -0.07
    itag
    -0.06
    POSITIVE LOGITS
     somewhere
    0.10
     eventually
    0.10
     SOM
    0.09
     Eventually
    0.08
     SOME
    0.08
    som
    0.07
     surely
    0.07
    Eventually
    0.07
     sooner
    0.07
     eventual
    0.07
    Activations Density 0.019%

    No Known Activations