© 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. 129311
    Prev
    Next
    INDEX
    Explanations

    sentences with significant shifts in tone or subject matter

    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
    enet
    -0.07
    agment
    -0.07
    uitive
    -0.07
    füg
    -0.06
    ijing
    -0.06
    _Tick
    -0.06
     pestic
    -0.06
    /or
    -0.06
    mw
    -0.06
    екÑģи
    -0.06
    POSITIVE LOGITS
    azen
    0.07
    VML
    0.07
    maal
    0.06
     celib
    0.06
    SEQ
    0.06
    805
    0.06
     mere
    0.06
     importantly
    0.06
     unlike
    0.06
    endas
    0.06
    Activations Density 0.009%

    No Known Activations