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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43414
    Prev
    Next
    INDEX
    Explanations

    terms related to VPN technology and its features

    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
    ằng
    -0.08
    ibri
    -0.07
    etrofit
    -0.07
    彦
    -0.07
    ubbo
    -0.07
    upal
    -0.07
    loub
    -0.07
    alim
    -0.06
    eyle
    -0.06
    shot
    -0.06
    POSITIVE LOGITS
     kill
    0.11
     Kill
    0.11
     AES
    0.10
    Kill
    0.10
     military
    0.09
     jurisdiction
    0.09
     leak
    0.09
     DNS
    0.09
     Split
    0.09
     SOCK
    0.09
    Activations Density 0.005%

    No Known Activations