© 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 EvalsExportsinterp-engineNEWAPI 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. 76567
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript elements related to webpage structure and content

    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
    interop
    -0.07
    cipher
    -0.07
    issing
    -0.07
    uos
    -0.07
    бÑĸ
    -0.07
    ç·Ĵ
    -0.07
    amber
    -0.07
    ¦
    -0.07
    ecies
    -0.06
    ãģ£ãģ
    -0.06
    POSITIVE LOGITS
     Rut
    0.06
     resume
    0.06
    879
    0.06
     Resume
    0.06
    anka
    0.06
    urban
    0.06
    anks
    0.05
    lassen
    0.05
     musical
    0.05
     Yin
    0.05
    Activations Density 0.005%

    No Known Activations