© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93732
    Prev
    Next
    INDEX
    Explanations

    keywords and components related to questions in a programming context

    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
    .dex
    -0.07
    è¨ĺäºĭ
    -0.06
    UNIX
    -0.06
    aklı
    -0.06
     Terr
    -0.06
     Tune
    -0.06
    æİ¢
    -0.06
    .transfer
    -0.06
    ekten
    -0.06
     âĢ»
    -0.06
    POSITIVE LOGITS
     answers
    0.09
     answered
    0.08
    answers
    0.08
     question
    0.08
     questions
    0.08
     quiz
    0.07
    /question
    0.07
    é¢ĺ
    0.07
     answer
    0.07
     scored
    0.07
    Activations Density 0.016%

    No Known Activations