© 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 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. 106264
    Prev
    Next
    INDEX
    Explanations

    references to enjoying a drive with music

    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
     walks
    -0.07
     prior
    -0.07
     walk
    -0.06
     walker
    -0.06
     Walk
    -0.06
    roupe
    -0.06
    agra
    -0.06
    walk
    -0.06
     daily
    -0.06
     stamp
    -0.06
    POSITIVE LOGITS
     driving
    0.10
     Driving
    0.09
    -driving
    0.09
     lái
    0.09
    Driving
    0.08
     Steering
    0.08
    -road
    0.08
     navigator
    0.08
    :animated
    0.08
     road
    0.08
    Activations Density 0.012%

    No Known Activations