© 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. 130566
    Prev
    Next
    INDEX
    Explanations

    key terms related to processes and actions in coding and regulations

    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
     truly
    -0.07
    oin
    -0.07
     âĢ¦↵
    -0.07
    âĢ¦”
    -0.06
    conti
    -0.06
     second
    -0.06
     genuinely
    -0.06
     early
    -0.06
     genuine
    -0.06
     anything
    -0.06
    POSITIVE LOGITS
     tzv
    0.14
    called
    0.11
     ún
    0.10
     called
    0.10
     llam
    0.09
     sao
    0.09
    ÑĩиÑģ
    0.09
    -called
    0.08
    .cms
    0.08
    âĢĮâĢĮ
    0.08
    Activations Density 0.096%

    No Known Activations