© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57006
    Prev
    Next
    INDEX
    Explanations

    occurrences of JavaScript-related code snippets

    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
    olit
    -0.06
    awai
    -0.06
     BAT
    -0.06
    umat
    -0.06
    keh
    -0.06
    __("
    -0.06
    ç«ł
    -0.06
    -l
    -0.06
     stove
    -0.06
    realm
    -0.06
    POSITIVE LOGITS
    ModelProperty
    0.07
    814
    0.06
     ActiveForm
    0.06
    .ReadByte
    0.06
    UIScreen
    0.06
    Intl
    0.06
    nia
    0.06
    xima
    0.06
    .setDefault
    0.06
     âĵĺ
    0.06
    Activations Density 0.002%

    No Known Activations