© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61684
    Prev
    Next
    INDEX
    Explanations

    temperature-related measurements and 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
    ãģıãģł
    -0.07
    лÑıн
    -0.07
    _framework
    -0.07
    msp
    -0.07
    upert
    -0.07
    odate
    -0.06
    OMUX
    -0.06
    mute
    -0.06
    iaux
    -0.06
    urus
    -0.06
    POSITIVE LOGITS
     temperature
    0.06
     Shelf
    0.06
    hrad
    0.06
    áh
    0.06
     Indi
    0.06
     Coleman
    0.06
    \TestCase
    0.06
    ahan
    0.06
     æIJ
    0.05
     kang
    0.05
    Activations Density 0.019%

    No Known Activations