© 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. 125627
    Prev
    Next
    INDEX
    Explanations

    references to specific seasons in a context related to events or activities

    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
    ustin
    -0.07
    ters
    -0.07
    hey
    -0.07
    edom
    -0.07
    zy
    -0.06
    ystems
    -0.06
    -football
    -0.06
    /icon
    -0.06
    cola
    -0.06
    equal
    -0.06
    POSITIVE LOGITS
    -long
    0.14
    ality
    0.10
    long
    0.10
    naire
    0.10
    aire
    0.10
    /year
    0.10
    nal
    0.09
    ally
    0.09
    -ending
    0.09
    naires
    0.09
    Activations Density 0.030%

    No Known Activations