© 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. 86774
    Prev
    Next
    INDEX
    Explanations

    references to light sources and their characteristics

    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
    915
    -0.07
    Flush
    -0.06
    ãĥĭãĤ¢
    -0.06
     Sens
    -0.06
    Modules
    -0.06
     Pret
    -0.05
    akat
    -0.05
    ereco
    -0.05
    atoria
    -0.05
     Guns
    -0.05
    POSITIVE LOGITS
     candle
    0.13
     candles
    0.12
     lamp
    0.11
     lighting
    0.11
     Lighting
    0.10
     lamps
    0.10
    çģ¯
    0.10
    lamp
    0.10
     lit
    0.09
     Lamp
    0.09
    Activations Density 0.024%

    No Known Activations