© 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. 57860
    Prev
    Next
    INDEX
    Explanations

    mentions of corporate leadership changes

    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
    kud
    -0.08
    igham
    -0.07
    posables
    -0.07
    FormsModule
    -0.07
    umbed
    -0.07
     ฿
    -0.07
    ungan
    -0.07
    ibraries
    -0.07
    oze
    -0.07
     wasted
    -0.06
    POSITIVE LOGITS
    ibil
    0.06
     bow
    0.06
     tired
    0.06
     family
    0.06
     Fresh
    0.06
     decision
    0.06
     now
    0.06
     HS
    0.06
    atak
    0.06
     change
    0.05
    Activations Density 0.018%

    No Known Activations