© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28901
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential outcomes or likelihoods

    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
    uss
    -0.06
     Ow
    -0.06
    еÑĢом
    -0.06
    dal
    -0.06
    ela
    -0.06
    ill
    -0.06
    enz
    -0.06
    uida
    -0.06
    Guide
    -0.06
    alls
    -0.06
    POSITIVE LOGITS
     blame
    0.08
    ouv
    0.07
     defenders
    0.07
    getSingleton
    0.07
    yen
    0.06
     harmless
    0.06
     okay
    0.06
     goede
    0.06
    extField
    0.06
     tolerant
    0.06
    Activations Density 0.034%

    No Known Activations