© 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. 83051
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts or terms related to law

    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
    ovÃŃ
    -0.07
    елен
    -0.07
    ambi
    -0.07
    ovÄĽ
    -0.07
    #ac
    -0.06
    Ñīей
    -0.06
     Zur
    -0.06
    æĸĩçĮ®
    -0.06
    jang
    -0.06
    subjects
    -0.06
    POSITIVE LOGITS
    anta
    0.06
    iec
    0.06
     continu
    0.06
    uplicate
    0.06
    ettel
    0.06
    ator
    0.06
    411
    0.06
     useClass
    0.06
    AND
    0.06
     doubles
    0.05
    Activations Density 0.011%

    No Known Activations