© 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. 84295
    Prev
    Next
    INDEX
    Explanations

    expressions of high levels of excitement or excellence

    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
    atis
    -0.07
    istrovstvÃŃ
    -0.07
    laden
    -0.07
    istration
    -0.06
    438
    -0.06
    vary
    -0.06
    uga
    -0.06
    uft
    -0.06
    858
    -0.06
    dden
    -0.06
    POSITIVE LOGITS
    (exc
    0.08
     exc
    0.08
     excit
    0.08
    uber
    0.07
    -exc
    0.07
    trak
    0.07
    itation
    0.07
     Exc
    0.07
    趣
    0.07
    gettext
    0.07
    Activations Density 0.010%

    No Known Activations