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. 43517
    Prev
    Next
    INDEX
    Explanations

    references to nuclear weapons and related geopolitical tensions

    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
    .vs
    -0.07
    exion
    -0.07
    ReturnType
    -0.06
    éIJµ
    -0.06
     RTBU
    -0.06
     Beled
    -0.06
    šak
    -0.06
    amanho
    -0.06
    PageIndex
    -0.06
     travellers
    -0.06
    POSITIVE LOGITS
     nuclear
    0.14
     enrichment
    0.14
     uranium
    0.13
     weapons
    0.12
     breakout
    0.12
     centrif
    0.12
     atomic
    0.11
     bomb
    0.11
     program
    0.11
     enrich
    0.11
    Activations Density 0.023%

    No Known Activations