© 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. 3626
    Prev
    Next
    INDEX
    Explanations

    phrases relating to obstacles or challenges in personal growth or societal issues

    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
    λοÏį
    -0.08
    anness
    -0.07
    .Xaml
    -0.07
    owell
    -0.07
    èħ
    -0.07
    \Blueprint
    -0.07
    iego
    -0.06
    kes
    -0.06
    ilo
    -0.06
    gas
    -0.06
    POSITIVE LOGITS
     unto
    0.07
     whom
    0.07
     proverb
    0.06
    576
    0.06
    357
    0.06
     incarn
    0.06
     rotating
    0.06
     bul
    0.06
    ANGER
    0.06
    acci
    0.05
    Activations Density 0.057%

    No Known Activations