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. 95529
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to environmental measurements, particularly humidity and weather conditions

    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
    ooke
    -0.07
    lacak
    -0.07
    geber
    -0.07
    æŃ³
    -0.07
    ''"
    -0.07
    noopener
    -0.07
     çķĻ
    -0.07
    â̦↵↵↵
    -0.07
    omain
    -0.07
     Redistributions
    -0.07
    POSITIVE LOGITS
     groom
    0.06
    kker
    0.06
     interrog
    0.06
    uten
    0.06
     sew
    0.06
     --
    0.06
     Companion
    0.06
     Merk
    0.06
     ast
    0.06
     ex
    0.05
    Activations Density 0.001%

    No Known Activations