© 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. 87848
    Prev
    Next
    INDEX
    Explanations

    phrases related to excerpts and adapting content from various sources

    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
    097
    -0.06
     réfé
    -0.06
    Ä°Z
    -0.06
    939
    -0.06
    738
    -0.06
     sheep
    -0.06
    áŀ¶áŀ
    -0.06
    lingen
    -0.05
    ×IJ
    -0.05
    endale
    -0.05
    POSITIVE LOGITS
     conversations
    0.07
    .scalablytyped
    0.07
     conversation
    0.07
    èĢIJ
    0.07
     interview
    0.07
    __/
    0.06
    rieb
    0.06
     UNUSED
    0.06
     thereof
    0.06
    ync
    0.06
    Activations Density 0.014%

    No Known Activations