© 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. 106189
    Prev
    Next
    INDEX
    Explanations

    references to the Qt framework and its components in programming contexts

    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
    ido
    -0.06
     i
    -0.06
    ca
    -0.06
    rd
    -0.06
    ÂŃ
    -0.06
    ish
    -0.06
     before
    -0.06
     on
    -0.05
    shaw
    -0.05
     for
    -0.05
    POSITIVE LOGITS
    리카
    0.08
    .ul
    0.08
    ultipartFile
    0.07
    WSC
    0.07
    |int
    0.07
    âķĿ
    0.07
     *\
    0.07
    aData
    0.07
    .dm
    0.07
    uraa
    0.07
    Activations Density 0.018%

    No Known Activations