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

    Neuronpedia

    Jacobian LensNEW
    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. 16412
    Prev
    Next
    INDEX
    Explanations

    mentions of new staff and their qualifications

    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
    irk
    -0.06
    еÑģп
    -0.06
    annual
    -0.06
     bypass
    -0.06
    ]){
    -0.06
    naments
    -0.06
    inesis
    -0.06
    ilion
    -0.06
     crud
    -0.06
     transformed
    -0.06
    POSITIVE LOGITS
     joining
    0.10
    joining
    0.10
     addition
    0.09
     join
    0.09
     newest
    0.09
     Join
    0.09
     additions
    0.09
     new
    0.08
     joins
    0.08
     our
    0.08
    Activations Density 0.038%

    No Known Activations