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. 9-LLAMASCOPE-RES-131K
    6. 95930
    Prev
    Next
    INDEX
    Explanations

    Java keywords and structure in code

    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
    .Sm
    -0.07
     Lori
    -0.07
    753
    -0.06
    iosa
    -0.06
    /sm
    -0.06
    Ĥæķ°
    -0.06
    ture
    -0.06
    üml
    -0.06
    æ§
    -0.06
    408
    -0.06
    POSITIVE LOGITS
    éĥ
    0.07
     exped
    0.07
    yer
    0.06
    Ùħر
    0.06
     gn
    0.06
    plotlib
    0.06
    yun
    0.06
    KK
    0.06
    egr
    0.06
    awl
    0.06
    Activations Density 0.001%

    No Known Activations