© 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. 60652
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their professional qualifications or experiences

    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
    ÑĢаÑĩ
    -0.07
    ád
    -0.06
    ehler
    -0.06
    ิà¹ī
    -0.06
    ÙĪزÛĮ
    -0.06
     ApplicationException
    -0.06
    ieve
    -0.06
    tron
    -0.06
     Fle
    -0.06
    \Foundation
    -0.06
    POSITIVE LOGITS
     Clients
    0.07
    ç»ıéªĮ
    0.07
     clients
    0.06
    -rounded
    0.06
    ä¸ĸ
    0.06
    etsk
    0.06
    ìĩ
    0.06
    Clients
    0.06
     RPC
    0.06
    -client
    0.06
    Activations Density 0.010%

    No Known Activations