© 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. 105748
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts and dates

    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
    ily
    -0.07
     Zar
    -0.07
    λεκ
    -0.06
    eth
    -0.06
    aghan
    -0.06
    rani
    -0.06
    ets
    -0.06
    erville
    -0.06
    midd
    -0.06
    sect
    -0.06
    POSITIVE LOGITS
     mÃł
    0.07
     that
    0.07
     where
    0.06
    usercontent
    0.06
     spent
    0.06
     où
    0.06
    èĥ¶
    0.06
    ī
    0.06
    ãģ§ãģ®
    0.06
    522
    0.06
    Activations Density 0.061%

    No Known Activations