© 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. 9-LLAMASCOPE-RES-131K
    11. 96737
    Prev
    Next
    INDEX
    Explanations

    references to legal parties involved in a lawsuit

    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
    anean
    -0.09
    ÑĢави
    -0.07
    leans
    -0.07
    ema
    -0.07
    LEAN
    -0.07
    verage
    -0.07
    erus
    -0.07
    nos
    -0.07
    hower
    -0.07
    ãĥ³ãĤ¯
    -0.07
    POSITIVE LOGITS
     Lol
    0.06
     Anders
    0.06
    ixe
    0.06
    onec
    0.06
    à¤Ŀ
    0.06
    ewith
    0.06
    653
    0.05
    veis
    0.05
    uter
    0.05
     ambigu
    0.05
    Activations Density 0.012%

    No Known Activations