© 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. 70016
    Prev
    Next
    INDEX
    Explanations

    references to official documentation and reports

    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
     Pump
    -0.06
    ardi
    -0.05
     enf
    -0.05
     tod
    -0.05
     &
    -0.05
     gum
    -0.05
     Shaft
    -0.05
    ard
    -0.05
    esch
    -0.05
    etal
    -0.05
    POSITIVE LOGITS
    izont
    0.08
    åĤ
    0.07
    adin
    0.07
    undra
    0.07
    iali
    0.07
    à¸ģระ
    0.07
    ediator
    0.06
    ãĥ³ãĥĢ
    0.06
     Mey
    0.06
    ubuntu
    0.06
    Activations Density 0.001%

    No Known Activations