© 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. 88518
    Prev
    Next
    INDEX
    Explanations

    mentions of vehicle safety features and performance specifications

    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
    ãĥ©ãĥĥãĤ¯
    -0.08
    кÑĥÑĢ
    -0.08
    ayah
    -0.07
    ãĥ©ãĤ¹
    -0.07
    SITE
    -0.07
    kses
    -0.06
    è¾°
    -0.06
    rets
    -0.06
    Carthy
    -0.06
    ÙģØ´
    -0.06
    POSITIVE LOGITS
    onis
    0.07
     ro
    0.06
    atest
    0.06
    oger
    0.06
     Ro
    0.06
    ¼
    0.06
     Dev
    0.06
    -txt
    0.05
    ie
    0.05
    anted
    0.05
    Activations Density 0.208%

    No Known Activations