© 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. 58583
    Prev
    Next
    INDEX
    Explanations

    concepts related to perseverance and strength

    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
     sui
    -0.07
     Skip
    -0.07
    AGO
    -0.06
    usz
    -0.06
     Halk
    -0.06
    RON
    -0.06
    ron
    -0.06
    hack
    -0.06
    ãĢĩ
    -0.06
    205
    -0.06
    POSITIVE LOGITS
     hence
    0.07
    symbol
    0.06
    agu
    0.06
     whereas
    0.06
    .UnitTesting
    0.06
     Ñģимвол
    0.06
    theme
    0.06
     Hence
    0.06
     Symbol
    0.06
     Jung
    0.06
    Activations Density 0.043%

    No Known Activations