© 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 EvalsExportsinterp-engineNEWAPI 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. 94948
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional reactions or strong feelings expressed towards other characters or events

    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
    indow
    -0.06
    TTY
    -0.06
    âĨIJ
    -0.05
     rz
    -0.05
    EMON
    -0.05
    éļ
    -0.05
    empl
    -0.05
    rg
    -0.05
     Nag
    -0.05
    nesia
    -0.05
    POSITIVE LOGITS
     threads
    0.09
    å¸ĸ
    0.08
     Thread
    0.08
     thread
    0.08
     THREAD
    0.08
     Threads
    0.08
    ynch
    0.07
    Äĩi
    0.07
    bach
    0.07
    Thread
    0.07
    Activations Density 0.957%

    No Known Activations