© 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. 15-LLAMASCOPE-RES-131K
    11. 90733
    Prev
    Next
    INDEX
    Explanations

    programming structures and syntax related to data declarations and token definitions

    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
    chap
    -0.06
    unya
    -0.06
    trail
    -0.05
    duct
    -0.05
     conductivity
    -0.05
    775
    -0.05
    illi
    -0.05
     Conduct
    -0.05
    marvin
    -0.05
    Trim
    -0.05
    POSITIVE LOGITS
     poil
    0.09
     addCriterion
    0.08
     зави
    0.08
     kli
    0.08
    .hom
    0.07
    aney
    0.07
    berman
    0.07
    ÐĴаж
    0.07
     kontakte
    0.07
     Ekon
    0.07
    Activations Density 0.004%

    No Known Activations