© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127325
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations and structures related to community services and healthcare

    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
     Äijang
    -0.07
     tomorrow
    -0.07
    uish
    -0.07
    erge
    -0.07
    oen
    -0.06
     upcoming
    -0.06
     Recently
    -0.06
     Twice
    -0.06
    indr
    -0.06
    åĪļæīį
    -0.06
    POSITIVE LOGITS
     later
    0.19
    later
    0.17
     soon
    0.17
     initially
    0.15
    Initially
    0.15
    Later
    0.14
     Later
    0.14
     Initially
    0.14
     eventually
    0.14
    Soon
    0.13
    Activations Density 0.296%

    No Known Activations