© 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. 106694
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation, comparison, and measurement in a competitive context

    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
    пеÑĩ
    -0.08
    eel
    -0.08
     Tep
    -0.07
    osate
    -0.07
    ób
    -0.07
    culus
    -0.07
    ordin
    -0.07
    icerca
    -0.07
    lier
    -0.07
     Smy
    -0.06
    POSITIVE LOGITS
    (es
    0.10
    marks
    0.09
    ../../../
    0.08
    elm
    0.08
    lid
    0.08
    ultimate
    0.08
    ing
    0.08
    manship
    0.07
    oir
    0.07
    warm
    0.07
    Activations Density 0.006%

    No Known Activations