© 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. 130927
    Prev
    Next
    INDEX
    Explanations

    phrases related to software execution and transaction management in computing systems

    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
    xes
    -0.07
    ools
    -0.07
    acades
    -0.07
     YE
    -0.06
    consts
    -0.06
    bones
    -0.06
    asu
    -0.06
    ENTS
    -0.06
    oi
    -0.06
    aland
    -0.06
    POSITIVE LOGITS
    .run
    0.08
     run
    0.07
    è·ij
    0.07
     runs
    0.07
     runner
    0.07
    RUN
    0.07
    	run
    0.07
    viron
    0.07
    run
    0.06
     isolated
    0.06
    Activations Density 0.027%

    No Known Activations