© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16918
    Prev
    Next
    INDEX
    Explanations

    specific dates and times 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
     pys
    -0.07
     Lewis
    -0.07
    itat
    -0.07
    itti
    -0.07
     rahat
    -0.06
    dana
    -0.06
    _CONTROLLER
    -0.06
     trace
    -0.06
     jud
    -0.06
    à¹Ĥย
    -0.06
    POSITIVE LOGITS
    utor
    0.08
    سÙĬÙĨ
    0.07
    irt
    0.07
    èĬ³
    0.07
    adders
    0.07
    phia
    0.07
    pent
    0.07
    AGON
    0.06
    paren
    0.06
    _HALF
    0.06
    Activations Density 0.033%

    No Known Activations