© 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. 127986
    Prev
    Next
    INDEX
    Explanations

    instances of notable achievements or milestones related to performance and sports 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
    apia
    -0.07
    COND
    -0.07
    649
    -0.06
    ersen
    -0.06
    leurs
    -0.06
    ENSION
    -0.06
    elo
    -0.06
     Duy
    -0.06
    leur
    -0.06
    اÙĪر
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.09
     именно
    0.07
     ever
    0.06
    -ever
    0.06
     anywhere
    0.06
     vůbec
    0.06
     tonight
    0.06
    eted
    0.06
     Hindered
    0.06
     pent
    0.06
    Activations Density 0.027%

    No Known Activations