© 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. 87082
    Prev
    Next
    INDEX
    Explanations

    expressions related to evaluation and selection processes

    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
     both
    -0.07
    羣æŃ£
    -0.07
    vla
    -0.06
    ä»Ķ
    -0.06
     BOTH
    -0.06
    LEAR
    -0.06
    olla
    -0.06
    pedia
    -0.06
    ovat
    -0.06
    zers
    -0.06
    POSITIVE LOGITS
     merely
    0.09
    isol
    0.08
     superficial
    0.08
     alone
    0.08
    mere
    0.07
     mere
    0.07
    æŁIJ
    0.07
     somehow
    0.07
    icit
    0.07
     irgend
    0.07
    Activations Density 0.052%

    No Known Activations