© 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. 106687
    Prev
    Next
    INDEX
    Explanations

    references to countdowns or time-related 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
    overe
    -0.07
    339
    -0.07
    heit
    -0.06
    nop
    -0.06
    965
    -0.06
    -json
    -0.06
    -hooks
    -0.06
    ekk
    -0.06
     Impress
    -0.06
    Delayed
    -0.06
    POSITIVE LOGITS
    /count
    0.07
    orie
    0.07
    zer
    0.07
    gg
    0.07
    -down
    0.07
    ellar
    0.07
    inue
    0.07
    blink
    0.06
     Mant
    0.06
    hana
    0.06
    Activations Density 0.003%

    No Known Activations