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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62067
    Prev
    Next
    INDEX
    Explanations

    phrases related to driving safety and environmental awareness

    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
    shed
    -0.07
    ollywood
    -0.06
    zburg
    -0.06
     Processing
    -0.06
     Chair
    -0.06
    опол
    -0.06
    minus
    -0.06
     processing
    -0.06
     pcs
    -0.06
     Churchill
    -0.06
    POSITIVE LOGITS
     fuel
    0.10
    æ²¹
    0.09
     oil
    0.09
     Fuel
    0.09
     coast
    0.08
    fuel
    0.08
     gas
    0.08
     tune
    0.08
    Oil
    0.07
     Oil
    0.07
    Activations Density 0.015%

    No Known Activations