© 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. 129272
    Prev
    Next
    INDEX
    Explanations

    references to ongoing or emerging trends and their implications

    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
     Wahl
    -0.06
    ŀĭ
    -0.06
    ¬ģ
    -0.06
    ieu
    -0.06
    ieux
    -0.06
     Monter
    -0.05
     ode
    -0.05
    лÑĥг
    -0.05
     WAIT
    -0.05
    æĮ¯
    -0.05
    POSITIVE LOGITS
     continue
    0.20
     continuation
    0.19
    continue
    0.19
     continues
    0.18
     continuing
    0.17
     continued
    0.17
    	continue
    0.16
    继ç»Ń
    0.16
     trend
    0.15
     Continue
    0.15
    Activations Density 0.049%

    No Known Activations