© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41120
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to project proposals and grant applications

    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
    arel
    -0.08
    akte
    -0.08
    SDL
    -0.07
    ÑĪка
    -0.07
    itta
    -0.07
    atty
    -0.07
    anten
    -0.07
    irut
    -0.07
    appa
    -0.07
    ạp
    -0.07
    POSITIVE LOGITS
     proposed
    0.11
     proposal
    0.10
     project
    0.09
     propose
    0.08
     plan
    0.08
     proposes
    0.07
     planned
    0.07
     proposing
    0.07
     Proposed
    0.07
     proposals
    0.07
    Activations Density 0.008%

    No Known Activations