© 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. 22-LLAMASCOPE-RES-131K
    11. 3784
    Prev
    Next
    INDEX
    Explanations

    references to home heating and temperature control systems

    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
    hydr
    -0.06
    odash
    -0.06
     Garten
    -0.06
     апп
    -0.05
     Haz
    -0.05
     Immigration
    -0.05
    elian
    -0.05
    linik
    -0.05
     erosion
    -0.05
    um
    -0.05
    POSITIVE LOGITS
     comfort
    0.11
    Comfort
    0.10
    comfort
    0.10
     thermostat
    0.10
     Comfort
    0.10
     drafts
    0.09
     temperatures
    0.09
     temperature
    0.09
     comfortable
    0.09
     thất
    0.08
    Activations Density 0.010%

    No Known Activations