© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60536
    Prev
    Next
    INDEX
    Explanations

    statistical and mathematical concepts related to estimation and inequalities

    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
     kaps
    -0.07
    еÑĩно
    -0.07
    cak
    -0.07
    icode
    -0.07
    /gpl
    -0.07
    еле
    -0.07
     asiat
    -0.07
    ekil
    -0.07
    isko
    -0.07
    íĬ
    -0.07
    POSITIVE LOGITS
     applied
    0.06
    ayd
    0.06
     fact
    0.06
    è²
    0.06
     cor
    0.05
    aal
    0.05
     Guill
    0.05
    umblr
    0.05
     çŁ¥
    0.05
     çĨ
    0.05
    Activations Density 0.186%

    No Known Activations