© 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. 15-LLAMASCOPE-RES-131K
    11. 983
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions, particularly those associated with database operations and service implementations

    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
    osphere
    -0.07
    ocide
    -0.07
    referrer
    -0.06
     Dickinson
    -0.06
    STALL
    -0.06
     Globe
    -0.06
     contents
    -0.06
     Pear
    -0.06
    ergency
    -0.06
    еÑĢин
    -0.06
    POSITIVE LOGITS
    ugins
    0.07
    elper
    0.07
     sécur
    0.07
    andles
    0.07
    orts
    0.07
    achat
    0.06
    Transactional
    0.06
    ierge
    0.06
    contres
    0.06
    oise
    0.06
    Activations Density 0.002%

    No Known Activations