© 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. 71818
    Prev
    Next
    INDEX
    Explanations

    temporal references in a sports context

    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
    nze
    -0.07
    æ§
    -0.07
     twice
    -0.07
    ç°
    -0.07
    oftware
    -0.07
    uple
    -0.07
    nga
    -0.06
     rest
    -0.06
    atore
    -0.06
    eah
    -0.06
    POSITIVE LOGITS
    conds
    0.07
    ogn
    0.07
    onde
    0.06
    su
    0.06
    acerb
    0.06
    unde
    0.06
    ied
    0.06
    ovo
    0.06
    raz
    0.06
    à¸ĩ
    0.06
    Activations Density 0.004%

    No Known Activations