© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 2752
    Prev
    Next
    INDEX
    Explanations

    phrases related to starting or launching a business

    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
    .expires
    -0.07
    anzi
    -0.07
    prs
    -0.07
    unch
    -0.07
    iod
    -0.06
    oidal
    -0.06
    _Utils
    -0.06
    hangi
    -0.06
    ÑĤÑĥ
    -0.06
    uz
    -0.06
    POSITIVE LOGITS
     businesses
    0.07
     dialogue
    0.07
     fires
    0.07
     new
    0.06
     debates
    0.06
     wars
    0.06
     Businesses
    0.06
     dialog
    0.06
     conversation
    0.06
     journal
    0.06
    Activations Density 0.017%

    No Known Activations