© 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. 29867
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical locations and significant objects

    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
    733
    -0.06
     Pag
    -0.06
     Street
    -0.06
     traction
    -0.06
     (
    -0.06
     street
    -0.05
     tar
    -0.05
     Charles
    -0.05
    464
    -0.05
     lon
    -0.05
    POSITIVE LOGITS
    озем
    0.07
     náp
    0.07
    ocache
    0.07
     обÑĢа
    0.07
    ifact
    0.07
    'class
    0.07
    .bz
    0.07
    amble
    0.07
    aler
    0.07
    ($('<
    0.07
    Activations Density 0.014%

    No Known Activations