© 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. 78828
    Prev
    Next
    INDEX
    Explanations

    terms related to project completion processes and commissioning activities

    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
    chin
    -0.05
     wreck
    -0.05
     Cust
    -0.05
    ä¼ģ
    -0.05
     hyp
    -0.05
     cust
    -0.05
    wj
    -0.05
     brick
    -0.05
     Rede
    -0.05
     invalidate
    -0.05
    POSITIVE LOGITS
     final
    0.12
     finished
    0.11
     finishing
    0.10
    final
    0.10
    finalize
    0.09
    -final
    0.09
     FINAL
    0.09
     completed
    0.09
     finalized
    0.09
     finish
    0.09
    Activations Density 0.025%

    No Known Activations