© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94683
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to electronic devices

    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
    éĢĨ
    -0.06
    campaign
    -0.06
    opper
    -0.06
    /testing
    -0.06
    ibo
    -0.06
    urb
    -0.05
    orton
    -0.05
    519
    -0.05
    allet
    -0.05
    Campaign
    -0.05
    POSITIVE LOGITS
    仲
    0.08
    ARSE
    0.07
    .MixedReality
    0.07
    _RESOURCES
    0.07
     khoản
    0.07
    ajs
    0.07
    åĽ
    0.06
     Byl
    0.06
    .serialization
    0.06
    _Adjust
    0.06
    Activations Density 0.018%

    No Known Activations