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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105822
    Prev
    Next
    INDEX
    Explanations

    references to companies involved in electronic manufacturing and assembly

    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
    //{{
    -0.07
    eum
    -0.07
    umbo
    -0.07
    ocket
    -0.07
    usra
    -0.07
    viar
    -0.07
    amax
    -0.07
    ptal
    -0.06
    erah
    -0.06
    ä¹Ĺ
    -0.06
    POSITIVE LOGITS
     Assembly
    0.09
     assembly
    0.08
    å·¥
    0.08
    assembly
    0.07
     Gig
    0.07
     å·¥
    0.07
    Assembly
    0.07
     gig
    0.06
     UID
    0.06
     labor
    0.06
    Activations Density 0.003%

    No Known Activations