© 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. 15-LLAMASCOPE-RES-131K
    11. 62447
    Prev
    Next
    INDEX
    Explanations

    negative phrases and qualifiers in technology discussions

    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
    zier
    -0.07
     Pend
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    ÑĥÑĢÑĥ
    -0.06
    keit
    -0.06
    oire
    -0.06
    iros
    -0.06
    rong
    -0.06
     пен
    -0.06
     tob
    -0.06
    POSITIVE LOGITS
     cloud
    0.08
    -cloud
    0.07
    ogl
    0.07
    CAPE
    0.07
    /cloud
    0.07
     compute
    0.07
    CLUD
    0.06
    ÃŃch
    0.06
    385
    0.06
     Kens
    0.06
    Activations Density 0.004%

    No Known Activations