© 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. 87665
    Prev
    Next
    INDEX
    Explanations

    references to professional service and expertise

    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
    367
    -0.07
    uble
    -0.07
    567
    -0.06
    917
    -0.06
    77
    -0.06
    575
    -0.06
    marked
    -0.06
    meric
    -0.06
    777
    -0.06
    652
    -0.06
    POSITIVE LOGITS
     Sloan
    0.07
    Call
    0.07
    æĪij们çļĦ
    0.07
    ÙĬات
    0.07
    á»įt
    0.07
     kho
    0.07
     Call
    0.07
     nostra
    0.07
     наÑĪиÑħ
    0.07
    å¶
    0.07
    Activations Density 0.008%

    No Known Activations