© 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. 39753
    Prev
    Next
    INDEX
    Explanations

    technical elements or syntax in programming code

    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
    ach
    -0.07
    ake
    -0.06
     unre
    -0.06
    atern
    -0.06
    at
    -0.06
    ont
    -0.06
    974
    -0.06
    nt
    -0.06
    thon
    -0.06
     kicker
    -0.05
    POSITIVE LOGITS
    elight
    0.08
    ä¸ļ
    0.07
    boom
    0.07
     éĸ
    0.07
    ิว
    0.07
    GraphNode
    0.07
    ÙĨÚ¯
    0.07
    .son
    0.07
    ickerView
    0.07
    GPL
    0.07
    Activations Density 0.001%

    No Known Activations