© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4139
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and anticipation related to entertainment content

    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
    rado
    -0.06
     sovereign
    -0.06
    ardown
    -0.06
    uggy
    -0.06
    ughs
    -0.06
    ึ
    -0.05
     stage
    -0.05
    olum
    -0.05
     Ferd
    -0.05
    /classes
    -0.05
    POSITIVE LOGITS
     news
    0.08
    announcement
    0.07
     announced
    0.07
    orden
    0.07
     announcement
    0.07
    allis
    0.07
     Lange
    0.07
    INO
    0.07
     fans
    0.07
    _queues
    0.07
    Activations Density 0.034%

    No Known Activations