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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106320
    Prev
    Next
    INDEX
    Explanations

    specific days of the week and significant dates

    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
    λιά
    -0.07
    aram
    -0.07
    tas
    -0.07
    âĢ¢↵↵
    -0.06
    705
    -0.06
    uang
    -0.06
    شتÙĩ
    -0.06
    æľ
    -0.06
    andi
    -0.06
    Echo
    -0.06
    POSITIVE LOGITS
    igon
    0.09
    edio
    0.07
    ancia
    0.07
     shortly
    0.06
    ÌĨ
    0.06
    ipt
    0.06
    	throws
    0.06
     TODAY
    0.06
     compliments
    0.06
     Hath
    0.06
    Activations Density 0.037%

    No Known Activations