© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72504
    Prev
    Next
    INDEX
    Explanations

    language related to technological innovation and advancements

    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
    _weak
    -0.06
    _xs
    -0.06
    athan
    -0.06
    renom
    -0.06
     scen
    -0.06
    ultiply
    -0.06
     Dexter
    -0.06
    appa
    -0.06
    ymes
    -0.06
     Kun
    -0.06
    POSITIVE LOGITS
     Designs
    0.09
     evolution
    0.09
     designs
    0.09
     design
    0.09
     Evolution
    0.08
     development
    0.08
     designers
    0.08
     Design
    0.08
     improvements
    0.08
    IDEO
    0.08
    Activations Density 0.019%

    No Known Activations