Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95668
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to contractual agreements and modifications

    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
    ette
    -0.07
    uno
    -0.06
    itten
    -0.06
    ös
    -0.06
    itor
    -0.06
    رÙģØª
    -0.06
    otten
    -0.06
    itur
    -0.06
     lượt
    -0.06
    allen
    -0.06
    POSITIVE LOGITS
     bü
    0.06
    ungi
    0.06
     اÙĦعÙĤ
    0.06
    åij¼
    0.06
    ä»
    0.06
    ëįĶëĭĪ
    0.06
    UNG
    0.06
    Multiplicity
    0.06
    Deg
    0.06
    pir
    0.06
    Activations Density 0.034%

    No Known Activations