© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    words associated with timing or sequences in actions

    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
     æľ¬
    -0.06
    ORK
    -0.06
    frog
    -0.06
    ãĢģæľ¬
    -0.06
    æľ¬
    -0.06
    thon
    -0.06
     gar
    -0.06
    alse
    -0.05
    본
    -0.05
     pert
    -0.05
    POSITIVE LOGITS
     these
    0.17
     Äijó
    0.17
     ấy
    0.16
    è¿Ļç§į
    0.16
     such
    0.15
     tersebut
    0.15
    these
    0.15
    è¿Ļä¸Ģ
    0.14
     Ø°ÙĦÙĥ
    0.14
     this
    0.14
    Activations Density 0.003%

    No Known Activations