© 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. 57450
    Prev
    Next
    INDEX
    Explanations

    coding and programming elements related to software 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
    iš
    -0.06
    592
    -0.06
    oplast
    -0.05
    abin
    -0.05
    chas
    -0.05
    orama
    -0.05
    etal
    -0.05
    ito
    -0.05
    hee
    -0.05
    pla
    -0.05
    POSITIVE LOGITS
    èįIJ
    0.08
    036
    0.07
    asper
    0.07
    ãĥ«ãĤ¯
    0.07
     нада
    0.07
    rei
    0.07
    лини
    0.07
    ATUS
    0.07
    AndView
    0.07
    ìn
    0.07
    Activations Density 0.000%

    No Known Activations