© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90414
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding issues

    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
     dán
    -0.09
    ecast
    -0.09
    .unsplash
    -0.08
    ÅĻÃŃz
    -0.08
    atel
    -0.08
     kvin
    -0.08
    idis
    -0.08
    elmet
    -0.08
    izio
    -0.08
    .appspot
    -0.08
    POSITIVE LOGITS
     â̦↵
    0.07
    â̦↵
    0.07
     o
    0.06
     m
    0.06
     [â̦]↵
    0.06
     s
    0.05
     Minor
    0.05
     “
    0.05
     ...↵
    0.05
     Ellen
    0.05
    Activations Density 0.587%

    No Known Activations