© 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. 98239
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of resilience and perseverance

    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
     ill
    -0.08
    plib
    -0.06
     bubble
    -0.06
    ãģªãĤī
    -0.06
    vik
    -0.06
    fty
    -0.05
    &E
    -0.05
     closure
    -0.05
     homo
    -0.05
    closure
    -0.05
    POSITIVE LOGITS
    itou
    0.07
    urette
    0.07
    apan
    0.07
     metaphor
    0.07
     nackte
    0.06
    anner
    0.06
    bole
    0.06
     analogy
    0.06
    EXPECT
    0.06
    _accessible
    0.06
    Activations Density 0.109%

    No Known Activations