© 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. 116365
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "or," indicating options or choices

    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
    ãģŁãĤĬ
    -0.07
    NK
    -0.07
    ÙĪÙĨÙĩ
    -0.07
    iedade
    -0.07
    ói
    -0.07
    mite
    -0.07
    asel
    -0.07
    ivé
    -0.07
    нÑİ
    -0.07
    è²
    -0.06
    POSITIVE LOGITS
     until
    0.10
     Until
    0.09
    until
    0.08
     wing
    0.07
    Until
    0.07
     according
    0.07
    _until
    0.07
     whenever
    0.06
    998
    0.06
     till
    0.06
    Activations Density 0.003%

    No Known Activations