© 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 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. 84403
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the search for solutions or improvements

    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
    deen
    -0.07
    termin
    -0.06
    <context
    -0.06
    .debian
    -0.05
     Bark
    -0.05
    å¥
    -0.05
    rompt
    -0.05
     devant
    -0.05
    à¥Īर
    -0.05
     Plants
    -0.05
    POSITIVE LOGITS
     ways
    0.13
     solutions
    0.13
     Solutions
    0.10
     solution
    0.10
    olutions
    0.10
     Ways
    0.09
     Solution
    0.09
    solution
    0.09
     answers
    0.09
     way
    0.08
    Activations Density 0.018%

    No Known Activations