© 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. 9-LLAMASCOPE-RES-131K
    11. 97884
    Prev
    Next
    INDEX
    Explanations

    references to the amount and characteristics of training data used in machine learning models

    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
    eph
    -0.07
     Lord
    -0.06
    -minded
    -0.06
     reporting
    -0.06
     dut
    -0.06
     LORD
    -0.06
     Fach
    -0.06
    iesz
    -0.05
    SED
    -0.05
     tou
    -0.05
    POSITIVE LOGITS
    úi
    0.08
    ScrollIndicator
    0.08
    айÑĤ
    0.08
    adoo
    0.07
    &W
    0.07
    PullParser
    0.07
    arella
    0.07
    ucer
    0.07
    Ïĥα
    0.07
    \grid
    0.07
    Activations Density 0.023%

    No Known Activations