© 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. 75979
    Prev
    Next
    INDEX
    Explanations

    technical components and specifications related to electronic devices and systems

    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
    uby
    -0.06
    наÑĤ
    -0.06
     embargo
    -0.05
     SOS
    -0.05
     method
    -0.05
     ga
    -0.05
     gent
    -0.05
    :
    -0.05
    tim
    -0.05
    reich
    -0.05
    POSITIVE LOGITS
    reau
    0.08
    panion
    0.07
    licants
    0.07
    multip
    0.07
    ToBounds
    0.07
    sold
    0.07
    .apiUrl
    0.07
    _mgmt
    0.07
    andon
    0.07
    ilip
    0.07
    Activations Density 0.043%

    No Known Activations