© 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. 119066
    Prev
    Next
    INDEX
    Explanations

    references to legal accountability and civil lawsuits for damages

    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
    arent
    -0.07
    apos
    -0.07
    ikel
    -0.07
    iris
    -0.07
    iverz
    -0.07
    iae
    -0.07
    itet
    -0.06
    azor
    -0.06
    åįļ士
    -0.06
     Ihr
    -0.06
    POSITIVE LOGITS
     suits
    0.09
     civil
    0.08
     consumer
    0.07
     suit
    0.07
    herits
    0.07
     Consumer
    0.06
     atom
    0.06
     suites
    0.06
     damages
    0.06
    vable
    0.06
    Activations Density 0.012%

    No Known Activations