© 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. 61259
    Prev
    Next
    INDEX
    Explanations

    references to numbers and numerical data

    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
    ยà¸ĩ
    -0.07
    Ùģات
    -0.07
    ÙĪØ·
    -0.07
    .onViewCreated
    -0.07
    encent
    -0.07
    imen
    -0.07
     Thornton
    -0.06
    DeltaTime
    -0.06
    activex
    -0.06
    UseProgram
    -0.06
    POSITIVE LOGITS
     plus
    0.08
     chances
    0.08
    this
    0.07
    plus
    0.07
    it
    0.06
     this
    0.06
     PLUS
    0.06
     odds
    0.06
     diesem
    0.06
     it
    0.06
    Activations Density 0.031%

    No Known Activations