© 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. 108120
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific quantities or units of measurement

    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
     to
    -0.07
     Conte
    -0.06
    /light
    -0.06
     du
    -0.05
    igmatic
    -0.05
     plant
    -0.05
     refr
    -0.05
    605
    -0.05
    hell
    -0.05
    .Concurrent
    -0.05
    POSITIVE LOGITS
    æĸ¼
    0.10
    äºİ
    0.09
    atra
    0.08
     æĸ¼
    0.07
    ktop
    0.07
    ongs
    0.07
    spin
    0.07
    ecided
    0.07
    ISTA
    0.07
    estroy
    0.07
    Activations Density 0.027%

    No Known Activations