© 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. 22-LLAMASCOPE-RES-131K
    11. 3595
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and code structure

    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
    habi
    -0.08
     Zus
    -0.07
    NES
    -0.07
    ustos
    -0.07
    erty
    -0.07
    adox
    -0.07
    erea
    -0.07
    .flash
    -0.07
    hover
    -0.07
    achuset
    -0.07
    POSITIVE LOGITS
     {@
    0.08
     Marsh
    0.06
    marsh
    0.06
    {@
    0.06
     Sherlock
    0.06
    classname
    0.06
    å»Ĭ
    0.06
     Kraft
    0.06
     activity
    0.06
    Å¡k
    0.06
    Activations Density 0.001%

    No Known Activations