© 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. 58848
    Prev
    Next
    INDEX
    Explanations

    expressions of anticipation, excitement, and engagement with books or films

    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
    rome
    -0.07
    imd
    -0.06
    omer
    -0.06
     anecd
    -0.06
     Mine
    -0.06
    ni
    -0.06
    rib
    -0.06
    atters
    -0.05
     everyday
    -0.05
    uro
    -0.05
    POSITIVE LOGITS
    ä½ľèĢħ
    0.09
     Yön
    0.08
    AutoSize
    0.07
    ाà¤Ĭ
    0.07
    readcr
    0.07
    saldo
    0.07
    osg
    0.07
     пÑĢоиз
    0.07
    ller
    0.07
    ноÑģÑı
    0.07
    Activations Density 0.036%

    No Known Activations