© 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. 15-LLAMASCOPE-RES-131K
    11. 27374
    Prev
    Next
    INDEX
    Explanations

    measurements and descriptions related to physical dimensions

    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
    itto
    -0.07
    readcr
    -0.07
    opsy
    -0.07
    uyu
    -0.07
    rott
    -0.06
    itarian
    -0.06
    .baidu
    -0.06
    .fun
    -0.06
    kehr
    -0.06
    169
    -0.06
    POSITIVE LOGITS
     Feder
    0.06
    _erase
    0.06
    onas
    0.06
     Benedict
    0.06
     Bennett
    0.06
     measures
    0.06
    fld
    0.06
     minus
    0.05
    vá
    0.05
    utzer
    0.05
    Activations Density 0.011%

    No Known Activations