© 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. 90411
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court cases

    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
     plu
    -0.06
    ulan
    -0.06
     ton
    -0.05
     prosecuting
    -0.05
     liquidity
    -0.05
     appellate
    -0.05
     neb
    -0.05
     knowledge
    -0.05
    747
    -0.05
    777
    -0.05
    POSITIVE LOGITS
    mojom
    0.09
    uforia
    0.08
    ovsky
    0.08
    ertino
    0.07
    ospace
    0.07
    0.07
    KHTML
    0.07
    awi
    0.07
    GBK
    0.07
    oulos
    0.07
    Activations Density 0.007%

    No Known Activations