© 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. 119894
    Prev
    Next
    INDEX
    Explanations

    programming concepts and elements

    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
    urret
    -0.06
    ousse
    -0.06
     permalink
    -0.06
    zell
    -0.06
     Taken
    -0.05
     chez
    -0.05
     ||=
    -0.05
    utters
    -0.05
    Mgr
    -0.05
    Å©
    -0.05
    POSITIVE LOGITS
    rong
    0.08
     /*#__
    0.07
    rit
    0.07
    uania
    0.07
    endir
    0.07
    opot
    0.07
    erness
    0.07
    aný
    0.07
    escal
    0.07
    ehr
    0.07
    Activations Density 0.000%

    No Known Activations