© 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. 40218
    Prev
    Next
    INDEX
    Explanations

    keywords related to research, support for students, and effective interventions for community improvement

    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
    ...↵↵↵↵
    -0.07
    ...↵↵↵
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
     Nail
    -0.07
    Ìī
    -0.07
     cele
    -0.06
    ả
    -0.06
    lý
    -0.06
    onn
    -0.06
    âĢ¦↵↵↵
    -0.06
    POSITIVE LOGITS
     hopefully
    0.07
     truly
    0.07
     important
    0.07
     tomorrow
    0.06
     otherwise
    0.06
     Hose
    0.06
     OTHERWISE
    0.06
    beit
    0.06
     potentially
    0.06
    ustral
    0.06
    Activations Density 0.019%

    No Known Activations