© 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. 87914
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structures

    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
    584
    -0.07
    indre
    -0.07
    kening
    -0.07
    olatile
    -0.07
    ansom
    -0.07
    iful
    -0.07
     Corpus
    -0.07
    ambre
    -0.06
    rego
    -0.06
    -fontawesome
    -0.06
    POSITIVE LOGITS
     CF
    0.07
    mall
    0.06
    δÏĮ
    0.06
     Dublin
    0.06
     Kerr
    0.06
     ApplicationException
    0.06
     kern
    0.06
    ickey
    0.06
     corre
    0.06
     Morav
    0.05
    Activations Density 0.003%

    No Known Activations