© 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. 59664
    Prev
    Next
    INDEX
    Explanations

    mentions of household appliances and their features

    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
     Helmet
    -0.07
    orer
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    awner
    -0.06
    á»ijc
    -0.06
    /feed
    -0.06
    ãĥªãĤ«
    -0.06
     Prepared
    -0.06
    raç
    -0.06
    ÄĽtÃŃ
    -0.06
    POSITIVE LOGITS
    oven
    0.07
    built
    0.06
     built
    0.06
    enci
    0.06
    ede
    0.06
     convenience
    0.06
    rieve
    0.06
    utherland
    0.06
    apk
    0.06
    ometr
    0.05
    Activations Density 0.006%

    No Known Activations