© 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. 91863
    Prev
    Next
    INDEX
    Explanations

    connections to decisions and their underlying principles

    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
    /respond
    -0.07
    æħ
    -0.07
    ìŀ¥
    -0.07
    xes
    -0.07
    ivia
    -0.07
    ạn
    -0.07
    ë
    -0.06
    ìŀ¥ìĿ´
    -0.06
    524
    -0.06
    upe
    -0.06
    POSITIVE LOGITS
     consideration
    0.16
     considerations
    0.12
     discussion
    0.10
     description
    0.09
     understanding
    0.09
     comparison
    0.08
     study
    0.08
     concern
    0.08
     consider
    0.08
     mention
    0.08
    Activations Density 0.073%

    No Known Activations