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. 22-LLAMASCOPE-RES-131K
    6. 5493
    Prev
    Next
    INDEX
    Explanations

    references to technology and safety in the workplace

    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
    .scalablytyped
    -0.07
     satisf
    -0.06
    ynthesis
    -0.06
    .Selenium
    -0.06
    вод
    -0.06
     dial
    -0.06
     tele
    -0.06
    ceph
    -0.06
     conexao
    -0.06
     margin
    -0.06
    POSITIVE LOGITS
     Indoor
    0.12
     indoor
    0.11
    acons
    0.10
    Floor
    0.09
     beacon
    0.09
     indoors
    0.08
    Outdoor
    0.08
    itag
    0.08
    .Floor
    0.08
     Floor
    0.08
    Activations Density 0.008%

    No Known Activations