© 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. 57341
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical terminologies related to structures and functions

    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
    Å¡ku
    -0.08
    ovny
    -0.08
    omp
    -0.08
    inke
    -0.07
    bette
    -0.07
    inue
    -0.07
    Sharper
    -0.07
    reta
    -0.07
     eskort
    -0.07
    èĵ
    -0.07
    POSITIVE LOGITS
     into
    0.10
     become
    0.09
     becomes
    0.09
    bec
    0.08
    into
    0.07
     became
    0.07
     becoming
    0.07
     Become
    0.07
     turns
    0.07
    Become
    0.06
    Activations Density 0.042%

    No Known Activations