© 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. 72207
    Prev
    Next
    INDEX
    Explanations

    code snippets or functions related to software or programming concepts

    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
    ỳ
    -0.08
    اÙĨÙĩ
    -0.06
     Levine
    -0.06
     VÅ¡ech
    -0.06
    еÑĤеÑĢб
    -0.06
    Unused
    -0.06
    å¶
    -0.06
    tutorial
    -0.06
     Lev
    -0.06
     Tut
    -0.06
    POSITIVE LOGITS
    0
    0.23
    00
    0.13
     zero
    0.12
    Û°
    0.12
    âĤĢ
    0.11
    ०
    0.11
    ï¼IJ
    0.10
    000
    0.10
    Ùł
    0.10
     Zero
    0.09
    Activations Density 0.143%

    No Known Activations