© 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. 15-LLAMASCOPE-RES-131K
    11. 61585
    Prev
    Next
    INDEX
    Explanations

    references to key individuals and their roles within organizations

    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
    asp
    -0.07
    Hunter
    -0.07
    ashi
    -0.07
    aser
    -0.07
    rance
    -0.07
    bbbb
    -0.07
    rike
    -0.07
    isans
    -0.07
    isia
    -0.06
    annya
    -0.06
    POSITIVE LOGITS
     founder
    0.08
     founders
    0.07
     head
    0.07
     propriet
    0.07
     cry
    0.07
     co
    0.07
     founding
    0.06
    inton
    0.06
    186
    0.06
    hton
    0.06
    Activations Density 0.023%

    No Known Activations