© 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. 17-LLAMASCOPE-RES-131K
    11. 79156
    Prev
    Next
    INDEX
    Explanations

    commands and flags related to programming and software execution

    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
    ãĥĥãĥĦ
    -0.08
    @nate
    -0.07
    ãĥ³ãĥĶ
    -0.07
    ipples
    -0.07
    acades
    -0.07
    aval
    -0.07
    -lfs
    -0.07
     latter
    -0.07
    sten
    -0.07
    ental
    -0.07
    POSITIVE LOGITS
    /--
    0.09
    /-
    0.08
    |--
    0.07
    aye
    0.06
    iba
    0.06
     "
    0.06
     "{\"
    0.06
    ίÏĦ
    0.06
    /+
    0.06
     minded
    0.06
    Activations Density 0.012%

    No Known Activations