© 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. 107398
    Prev
    Next
    INDEX
    Explanations

    large numerical values followed by the term 'million'

    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
    382
    -0.07
     gé
    -0.06
    aben
    -0.06
    pData
    -0.06
     entity
    -0.06
    aille
    -0.06
    apo
    -0.06
    онÑĥ
    -0.06
     ashes
    -0.06
    нина
    -0.06
    POSITIVE LOGITS
    aira
    0.07
    fak
    0.06
    iage
    0.06
    tainment
    0.06
     migrationBuilder
    0.05
     spir
    0.05
     GD
    0.05
    PIPE
    0.05
    管
    0.05
     Trip
    0.05
    Activations Density 0.000%

    No Known Activations