© 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. 17-LLAMASCOPE-RES-131K
    11. 2434
    Prev
    Next
    INDEX
    Explanations

    instances of arrival and waiting situations

    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
    ActionCreators
    -0.06
    795
    -0.06
     Gesch
    -0.06
    meyi
    -0.06
    bj
    -0.06
    elden
    -0.06
    ãĥ«ãĥĪ
    -0.06
    borg
    -0.06
     Zug
    -0.06
    ÙĨج
    -0.05
    POSITIVE LOGITS
     English
    0.07
     vá
    0.07
     Language
    0.07
    ARGIN
    0.07
     bilingual
    0.07
    IDI
    0.07
    exe
    0.06
     translation
    0.06
     Ministry
    0.06
    .requireNonNull
    0.06
    Activations Density 0.008%

    No Known Activations