© 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. 85161
    Prev
    Next
    INDEX
    Explanations

    first-person perspectives and reflections on personal experiences

    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
    uluk
    -0.08
     @_
    -0.06
    parate
    -0.05
    imi
    -0.05
    dash
    -0.05
    lig
    -0.05
    à¥ĭह
    -0.05
    FileNotFoundException
    -0.05
     Qu
    -0.05
    omy
    -0.05
    POSITIVE LOGITS
    838
    0.08
     absolutely
    0.07
     Thing
    0.07
    gart
    0.07
    acker
    0.07
    landa
    0.07
    veis
    0.07
     thing
    0.07
    azi
    0.07
     meis
    0.07
    Activations Density 0.012%

    No Known Activations