© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94352
    Prev
    Next
    INDEX
    Explanations

    specific time and date information related to 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
    heimer
    -0.07
    essler
    -0.07
    osten
    -0.07
     Ñģка
    -0.06
    ummings
    -0.06
    stal
    -0.06
    elerik
    -0.06
    omik
    -0.06
    upe
    -0.06
    emon
    -0.06
    POSITIVE LOGITS
    ORY
    0.07
    419
    0.06
     Hearth
    0.06
     DÃŃky
    0.06
    dech
    0.06
    pes
    0.06
    Deg
    0.06
    670
    0.06
     PÅĻi
    0.06
    CNT
    0.06
    Activations Density 0.008%

    No Known Activations