© 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. 77472
    Prev
    Next
    INDEX
    Explanations

    terms related to digital manipulation and creative processes in video and art production

    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
    éŁ¿
    -0.06
    èŃľ
    -0.06
    amet
    -0.06
    èĬ³
    -0.06
    IRC
    -0.06
     Preis
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    uhn
    -0.06
    UsageId
    -0.06
    ANTITY
    -0.06
    POSITIVE LOGITS
     Guid
    0.06
     scene
    0.06
    877
    0.06
     Seamless
    0.06
     weather
    0.06
    onto
    0.06
    istine
    0.06
     Matte
    0.06
    480
    0.06
     Triumph
    0.06
    Activations Density 0.010%

    No Known Activations