Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5254
    Prev
    Next
    INDEX
    Explanations

    technical terms related to code and programming functions

    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
    onis
    -0.08
    NSURLSession
    -0.08
    ADM
    -0.07
    à¹īà¸ĩ
    -0.07
     gifs
    -0.07
     snapchat
    -0.07
    åķª
    -0.07
    bable
    -0.06
     guard
    -0.06
    eway
    -0.06
    POSITIVE LOGITS
     iPod
    0.07
    hai
    0.07
    Specifier
    0.07
    =[[
    0.07
    utton
    0.07
    æħ
    0.06
     Tactics
    0.06
    200
    0.06
    Recognizer
    0.06
    å±ŀ
    0.06
    Activations Density 0.083%

    No Known Activations