© 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. 17649
    Prev
    Next
    INDEX
    Explanations

    references to programming or coding syntax

    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
    alon
    -0.08
    APPER
    -0.08
    arer
    -0.08
    å¿į
    -0.07
    ikler
    -0.07
    Å¡ti
    -0.07
     |_|
    -0.07
     uÄŁ
    -0.07
    ĥ
    -0.07
    CompleteListener
    -0.07
    POSITIVE LOGITS
    781
    0.06
     Raleigh
    0.06
     ere
    0.05
    iflower
    0.05
    aleigh
    0.05
     Flight
    0.05
    AutoSize
    0.05
    428
    0.05
     Libraries
    0.05
    251
    0.05
    Activations Density 0.000%

    No Known Activations