© 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. 29216
    Prev
    Next
    INDEX
    Explanations

    references to image resolutions and download instructions

    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
     forg
    -0.06
    coli
    -0.05
     Richt
    -0.05
     Trad
    -0.05
     th
    -0.05
    èn
    -0.05
    emons
    -0.05
    arro
    -0.05
     word
    -0.05
     laid
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    _firestore
    0.08
    (suite
    0.07
    ofire
    0.07
    rary
    0.07
     глаз
    0.07
    _managed
    0.07
    _advanced
    0.07
    _Command
    0.07
    lace
    0.07
    Activations Density 0.002%

    No Known Activations