© 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. 15-LLAMASCOPE-RES-131K
    11. 88714
    Prev
    Next
    INDEX
    Explanations

    inquiries or requests for additional information

    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
    STEM
    -0.07
    nett
    -0.07
    aki
    -0.07
     ActionTypes
    -0.07
    leur
    -0.06
    ynes
    -0.06
    ald
    -0.06
    аки
    -0.06
    VIC
    -0.06
    ¯ÃĤ
    -0.06
    POSITIVE LOGITS
     about
    0.07
    AGMA
    0.07
    uilder
    0.07
     patented
    0.06
     tightly
    0.06
    ystate
    0.06
     regarding
    0.06
     tentang
    0.06
    asin
    0.06
    ãĥ¼ãĤ¹
    0.06
    Activations Density 0.005%

    No Known Activations