© 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 EvalsExportsinterp-engineNEWAPI 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. 15309
    Prev
    Next
    INDEX
    Explanations

    keywords and function names related to programming and software development

    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
    ema
    -0.07
    ifestyles
    -0.06
    TeX
    -0.06
    aż
    -0.06
    j
    -0.06
    etty
    -0.06
    otec
    -0.06
    lo
    -0.05
    laden
    -0.05
    ape
    -0.05
    POSITIVE LOGITS
    NODE
    0.07
    NOP
    0.07
    zdy
    0.07
    ickerView
    0.06
     Hanson
    0.06
    åIJ¦
    0.06
     nackte
    0.06
    abis
    0.06
    plaintext
    0.06
    illian
    0.06
    Activations Density 0.002%

    No Known Activations