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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43767
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
     Portland
    -0.07
     Pasadena
    -0.07
    ampa
    -0.06
     Beirut
    -0.06
     CN
    -0.06
     Gerald
    -0.06
     Jer
    -0.06
    Portland
    -0.06
     Jerry
    -0.06
     Eugene
    -0.06
    POSITIVE LOGITS
     Loki
    0.21
     Marvel
    0.19
     Avengers
    0.18
    Marvel
    0.17
     Thor
    0.14
     Hulk
    0.14
     MCU
    0.13
    Thor
    0.13
     Spider
    0.12
     Norse
    0.12
    Activations Density 0.002%

    No Known Activations