© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107364
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and hope

    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
    amber
    -0.06
     Am
    -0.06
    vern
    -0.06
    alsy
    -0.06
    ember
    -0.05
     Bradford
    -0.05
    094
    -0.05
    gren
    -0.05
    lest
    -0.05
    Am
    -0.05
    POSITIVE LOGITS
    ä¸ĢåĪĩ
    0.08
    rescia
    0.07
    ulin
    0.07
     ActionTypes
    0.07
    олод
    0.06
    syscall
    0.06
    享
    0.06
     ÑĤв
    0.06
     ÙĪج
    0.06
     stripslashes
    0.06
    Activations Density 0.007%

    No Known Activations