© 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. 71211
    Prev
    Next
    INDEX
    Explanations

    mentions of video game content and updates

    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
    UGIN
    -0.08
    ursal
    -0.07
    ا
    -0.07
    uhe
    -0.07
    otos
    -0.07
    oling
    -0.06
    ibir
    -0.06
    ilen
    -0.06
    ves
    -0.06
    engu
    -0.06
    POSITIVE LOGITS
     Kl
    0.06
    orf
    0.06
     TypeInfo
    0.05
     Pent
    0.05
    asa
    0.05
    ĥģ
    0.05
     gob
    0.05
     Cle
    0.05
     ↵
    0.05
     mus
    0.05
    Activations Density 0.061%

    No Known Activations