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

    Neuronpedia

    Jacobian LensNEW
    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. 40365
    Prev
    Next
    INDEX
    Explanations

    code elements related to programming syntax and 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
     divergence
    -0.06
    ful
    -0.06
     Kr
    -0.06
    LO
    -0.06
    anos
    -0.06
    .native
    -0.06
     Hag
    -0.06
    en
    -0.06
    anth
    -0.05
    å½
    -0.05
    POSITIVE LOGITS
    оги
    0.07
    alon
    0.07
    endas
    0.07
    atica
    0.07
    uden
    0.07
    mlink
    0.07
    .Txt
    0.07
    .ErrorMessage
    0.07
    pras
    0.07
    égor
    0.06
    Activations Density 0.001%

    No Known Activations