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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5285
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in professional titles and roles

    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
     ones
    -0.06
    nder
    -0.06
    stery
    -0.06
    profession
    -0.06
    éĤ£äºĽ
    -0.06
    buz
    -0.06
    oth
    -0.06
    obody
    -0.06
     Ones
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
    sole
    0.10
     sole
    0.08
     fundraiser
    0.08
     chief
    0.07
     lead
    0.07
     main
    0.07
    verts
    0.07
     occasional
    0.06
    owns
    0.06
    chief
    0.06
    Activations Density 0.020%

    No Known Activations