© 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. 88122
    Prev
    Next
    INDEX
    Explanations

    educational roles and positions within various institutions

    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
     VÅ¡ech
    -0.09
    instanc
    -0.09
    datatable
    -0.08
    áme
    -0.08
    inspect
    -0.08
     Hlav
    -0.08
    ç§
    -0.08
    ábado
    -0.07
    edo
    -0.07
    átek
    -0.07
    POSITIVE LOGITS
     until
    0.13
     before
    0.12
    until
    0.11
     years
    0.11
     during
    0.10
     throughout
    0.10
     twice
    0.09
     prior
    0.09
    before
    0.09
     last
    0.09
    Activations Density 0.048%

    No Known Activations