© 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. 16708
    Prev
    Next
    INDEX
    Explanations

    references to specific minerals or geological materials

    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
    ings
    -0.07
     Wag
    -0.06
     Cri
    -0.06
    net
    -0.06
     Wir
    -0.06
     Ur
    -0.06
    ↵
    -0.06
     demi
    -0.06
    ÌĤ
    -0.06
    utter
    -0.06
    POSITIVE LOGITS
    ëĭĪëĭ¤
    0.08
    ibaba
    0.08
    olume
    0.07
     Tops
    0.07
    azor
    0.07
     quotations
    0.07
    اÙĦص
    0.07
    ìĭ¸
    0.07
    ropa
    0.07
    .qual
    0.07
    Activations Density 0.000%

    No Known Activations