© 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. 104136
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or information

    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
     indu
    -0.07
    ì¦Ŀ
    -0.06
    èĹı
    -0.06
    OTH
    -0.06
    ent
    -0.06
    135
    -0.06
    setQuery
    -0.06
     prov
    -0.05
    datagrid
    -0.05
     Reviews
    -0.05
    POSITIVE LOGITS
    eyse
    0.07
    aca
    0.07
    eum
    0.07
    ç·´
    0.07
    .weixin
    0.07
    airo
    0.07
    icari
    0.07
    esk
    0.07
    rych
    0.06
    mpar
    0.06
    Activations Density 0.011%

    No Known Activations