© 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 EvalsExportsAPI 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. 85615
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or statistics

    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
    enko
    -0.07
    imir
    -0.07
    kili
    -0.07
     Fee
    -0.06
    668
    -0.06
    imal
    -0.06
    ắc
    -0.06
     Balk
    -0.06
     Lean
    -0.06
    481
    -0.06
    POSITIVE LOGITS
    jun
    0.07
    ocker
    0.07
    ENU
    0.06
    upert
    0.06
    rd
    0.06
    ares
    0.06
    ÑĥÑģÑĤ
    0.06
    ichert
    0.06
    ãĢħ
    0.06
     avg
    0.06
    Activations Density 0.022%

    No Known Activations