© 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. 3508
    Prev
    Next
    INDEX
    Explanations

    references to governmental or official employment roles

    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
    CU
    -0.06
    loff
    -0.06
    reon
    -0.06
    λÏİ
    -0.06
    ovÃŃ
    -0.06
    елик
    -0.06
     COVID
    -0.06
    erman
    -0.06
    -symbol
    -0.06
     Ches
    -0.06
    POSITIVE LOGITS
     Bian
    0.07
     equipments
    0.07
     PROCUREMENT
    0.07
    ksam
    0.07
    ãĥ£
    0.06
    finity
    0.06
    æķ¦
    0.06
    akin
    0.06
    åľĴ
    0.06
    croft
    0.06
    Activations Density 0.000%

    No Known Activations