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. 43794
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limits or boundaries

    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
    hower
    -0.06
    Ø¢Ùħد
    -0.06
    anguages
    -0.06
    irst
    -0.06
    StartElement
    -0.06
    erdem
    -0.06
    REFER
    -0.06
    izoph
    -0.06
    atsapp
    -0.06
    urent
    -0.06
    POSITIVE LOGITS
     ordinary
    0.17
    ordinary
    0.14
     norm
    0.14
     ordin
    0.13
     ord
    0.12
     Ordinary
    0.11
     realm
    0.11
     ORD
    0.11
     extraordinary
    0.11
     norms
    0.11
    Activations Density 0.010%

    No Known Activations