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. 43779
    Prev
    Next
    INDEX
    Explanations

    references to vulnerability or security in a technical context

    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
    ầu
    -0.07
    αι
    -0.07
    arend
    -0.07
    AsStream
    -0.06
    eker
    -0.06
    orado
    -0.06
    .xls
    -0.06
    urette
    -0.06
    lsi
    -0.06
    ughter
    -0.06
    POSITIVE LOGITS
     trust
    0.10
     click
    0.09
     Trust
    0.09
    -click
    0.09
    Trust
    0.08
    -touch
    0.08
     clicks
    0.08
     trusts
    0.08
    click
    0.08
     knowledge
    0.08
    Activations Density 0.006%

    No Known Activations