© 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. 15-LLAMASCOPE-RES-131K
    11. 86866
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing sustainability and collective action

    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
    .abstract
    -0.07
    ITE
    -0.07
    icit
    -0.06
    اÙģر
    -0.06
    INTER
    -0.06
     بÙĪدÙĨ
    -0.06
    fal
    -0.06
    .indent
    -0.06
    Utilities
    -0.06
    ожд
    -0.06
    POSITIVE LOGITS
     better
    0.11
    better
    0.08
    eti
    0.08
     benefit
    0.08
     towards
    0.07
     further
    0.07
    Better
    0.07
     long
    0.07
     tomorrow
    0.07
     McL
    0.07
    Activations Density 0.026%

    No Known Activations