© 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. 4667
    Prev
    Next
    INDEX
    Explanations

    phrases that involve comparisons between items or concepts

    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
    ruk
    -0.07
    оби
    -0.07
    ساÙĨ
    -0.07
     reactive
    -0.07
    ساÙĨÛĮ
    -0.07
    orting
    -0.07
    daf
    -0.06
    eren
    -0.06
    Mathf
    -0.06
    Thunk
    -0.06
    POSITIVE LOGITS
    attice
    0.06
     å¾Ĵ
    0.06
    agine
    0.06
    contrast
    0.06
    guid
    0.06
    igure
    0.06
    ORB
    0.06
     Mild
    0.06
     Perm
    0.06
    ken
    0.06
    Activations Density 0.004%

    No Known Activations