© 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. 3554
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "instrumental" and its variations, indicating a focus on pivotal roles or contributions

    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
    ega
    -0.08
    etur
    -0.07
    enda
    -0.07
    ÑĮко
    -0.07
    yun
    -0.07
    eat
    -0.07
    esta
    -0.07
     vá»ijn
    -0.07
    à¸ļà¸ģ
    -0.07
    porto
    -0.07
    POSITIVE LOGITS
    /help
    0.08
    mente
    0.07
    yst
    0.07
    ized
    0.06
    illos
    0.06
    inux
    0.06
    ysts
    0.06
    adro
    0.06
    izing
    0.06
    apiro
    0.06
    Activations Density 0.001%

    No Known Activations