© 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. 93248
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "using" in various 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
    freeze
    -0.07
    rors
    -0.07
    eyh
    -0.06
    lesi
    -0.06
    orate
    -0.06
     Representative
    -0.06
    Ìģ
    -0.06
    .ts
    -0.06
    áng
    -0.06
     froze
    -0.06
    POSITIVE LOGITS
    icode
    0.07
    DIG
    0.07
    ìĥģìľĦ
    0.06
     Hazel
    0.06
     DependencyProperty
    0.06
     nest
    0.06
    زÙħ
    0.06
    ÙĨب
    0.06
     Couch
    0.06
    Aura
    0.06
    Activations Density 0.003%

    No Known Activations