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. 11459
    Prev
    Next
    INDEX
    Explanations

    terms related to spin and charge in quantum physics

    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
    istrovstvÃŃ
    -0.08
    erdale
    -0.08
    anca
    -0.07
    gaard
    -0.07
    typeName
    -0.07
    ypsum
    -0.07
     اÙĦرÙħزÙĬØ©
    -0.07
    ToBounds
    -0.07
    ysa
    -0.07
    ereotype
    -0.06
    POSITIVE LOGITS
    odal
    0.13
    tron
    0.12
    or
    0.11
    ors
    0.11
    tr
    0.11
    orial
    0.10
    ful
    0.10
    orbit
    0.10
    -or
    0.10
    dependent
    0.09
    Activations Density 0.011%

    No Known Activations