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. 22-LLAMASCOPE-RES-131K
    6. 5686
    Prev
    Next
    INDEX
    Explanations

    references to historical events and social conditions affecting Japan and its interactions with other countries

    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
    utos
    -0.07
    =title
    -0.07
     Redemption
    -0.07
     Korean
    -0.06
    hua
    -0.06
    obi
    -0.06
    itles
    -0.06
    UTES
    -0.06
    .hw
    -0.06
     diff
    -0.06
    POSITIVE LOGITS
     Carp
    0.07
    wick
    0.06
    ocu
    0.06
    ataka
    0.06
    ifar
    0.06
    .@
    0.06
    adro
    0.06
    landa
    0.06
    -transitional
    0.06
    лам
    0.06
    Activations Density 0.017%

    No Known Activations