© 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. 15-LLAMASCOPE-RES-131K
    11. 27202
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time

    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
    داد
    -0.06
    roduction
    -0.06
     longstanding
    -0.06
     spir
    -0.06
     lifelong
    -0.06
     lik
    -0.05
    #index
    -0.05
     Lewis
    -0.05
    mdir
    -0.05
     regress
    -0.05
    POSITIVE LOGITS
     Gap
    0.09
    gap
    0.09
     gap
    0.09
    cono
    0.09
    _gap
    0.09
    Gap
    0.08
    éļĶ
    0.08
    emb
    0.08
     gaps
    0.07
    ãĤ¦ãĤ¹
    0.07
    Activations Density 0.022%

    No Known Activations