© 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. 60664
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and court decisions

    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
    urai
    -0.08
    aight
    -0.07
    illes
    -0.07
    ÏĦεί
    -0.06
    ');?>
    -0.06
    isini
    -0.06
     stool
    -0.06
    inox
    -0.06
    tÃŃ
    -0.06
    iore
    -0.06
    POSITIVE LOGITS
     decision
    0.10
     decisions
    0.09
    decision
    0.08
     final
    0.08
     Decision
    0.08
     deciding
    0.07
     hopefully
    0.07
    åĨ³
    0.07
     decides
    0.07
     decide
    0.07
    Activations Density 0.029%

    No Known Activations