© 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. 16056
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æľį
    -0.08
    باØŃ
    -0.07
    ouch
    -0.07
     chấm
    -0.07
    unge
    -0.07
    UIL
    -0.06
    uttle
    -0.06
    ä¹ĭä¸Ģ
    -0.06
    æĮ
    -0.06
    lingen
    -0.06
    POSITIVE LOGITS
     upcoming
    0.10
     next
    0.09
     forthcoming
    0.08
     tomorrow
    0.08
    .scalablytyped
    0.08
    next
    0.07
     later
    0.07
    خص
    0.07
    dbus
    0.07
    TriState
    0.07
    Activations Density 0.028%

    No Known Activations