© 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. 57981
    Prev
    Next
    INDEX
    Explanations

    code elements related to class hierarchy and inheritance in programming

    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
    ew
    -0.08
    if
    -0.06
    to
    -0.06
    iller
    -0.06
    g
    -0.06
    for
    -0.05
    âĢ¦
    -0.05
    yn
    -0.05
     Weber
    -0.05
     near
    -0.05
    POSITIVE LOGITS
     bản
    0.09
     Ãľy
    0.09
    вад
    0.09
    ibase
    0.09
    ãĥ³ãĥIJ
    0.08
    ::__
    0.08
    ابر
    0.08
     superclass
    0.08
    okens
    0.08
    озем
    0.08
    Activations Density 0.009%

    No Known Activations