© 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. 82869
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific research and methodology

    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
    ầm
    -0.06
    urga
    -0.06
    -www
    -0.06
     Kro
    -0.06
    kar
    -0.06
    -
    -0.06
    dart
    -0.06
    peak
    -0.06
    057
    -0.06
    akin
    -0.06
    POSITIVE LOGITS
     tá»Ń
    0.07
    ëĭĪìĬ¤
    0.07
    Winvalid
    0.07
    iParam
    0.06
     Sesso
    0.06
    .createComponent
    0.06
    ucu
    0.06
    ’nda
    0.06
    롯
    0.06
    383
    0.06
    Activations Density 0.001%

    No Known Activations