© 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. 39568
    Prev
    Next
    INDEX
    Explanations

    chapter separators in a structured document layout

    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
    ãĤ»ãĥ³
    -0.07
    onen
    -0.07
    ingles
    -0.07
    astes
    -0.07
    uler
    -0.07
    czy
    -0.06
    ánÃŃ
    -0.06
     Inherits
    -0.06
    emia
    -0.06
    cales
    -0.06
    POSITIVE LOGITS
    adero
    0.07
    omp
    0.07
    ãĥ³ãĥķ
    0.07
     Hast
    0.06
    ipel
    0.06
    ocker
    0.06
    OMPI
    0.06
     ill
    0.06
    .CommandType
    0.06
    ichael
    0.06
    Activations Density 0.000%

    No Known Activations