© 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. 119308
    Prev
    Next
    INDEX
    Explanations

    references to significant locations or institutions

    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
    atra
    -0.07
    orman
    -0.07
    .scalablytyped
    -0.07
    .false
    -0.07
     oku
    -0.06
     kaps
    -0.06
     Aires
    -0.06
    ansi
    -0.06
    ADS
    -0.06
     misd
    -0.06
    POSITIVE LOGITS
     history
    0.09
     Asia
    0.08
     History
    0.08
     HISTORY
    0.07
     иÑģÑĤоÑĢии
    0.07
     anywhere
    0.07
    usal
    0.07
     existence
    0.07
     ever
    0.06
     Europe
    0.06
    Activations Density 0.017%

    No Known Activations