© 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. 15847
    Prev
    Next
    INDEX
    Explanations

    references to code generation and the associated metadata in documents

    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
    entine
    -0.06
     im
    -0.06
    urum
    -0.06
    etch
    -0.06
    ech
    -0.06
    uen
    -0.05
     Des
    -0.05
     floated
    -0.05
     floats
    -0.05
     des
    -0.05
    POSITIVE LOGITS
    .Generated
    0.09
    ãĥ¼ãĥ
    0.08
    Generated
    0.08
    /antlr
    0.08
     непоÑģÑĢед
    0.08
    -Cs
    0.07
    GRE
    0.07
    ISR
    0.07
    generated
    0.07
     resil
    0.07
    Activations Density 0.001%

    No Known Activations