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. 44282
    Prev
    Next
    INDEX
    Explanations

    programming function calls and event triggers in code

    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
     JAXBElement
    -0.07
    .microsoft
    -0.07
    avig
    -0.07
    _aes
    -0.07
     Vander
    -0.06
    Indiana
    -0.06
    éĨ´
    -0.06
    οκ
    -0.06
     Indiana
    -0.06
    :animated
    -0.06
    POSITIVE LOGITS
     Meteor
    0.21
     meteor
    0.20
    Meteor
    0.19
    meteor
    0.18
    eteor
    0.16
     Mongo
    0.11
     collections
    0.10
     collection
    0.10
     Reactive
    0.10
     Blaze
    0.10
    Activations Density 0.007%

    No Known Activations