© 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. 15134
    Prev
    Next
    INDEX
    Explanations

    references to programming frameworks and libraries

    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
    $MESS
    -0.09
     Synd
    -0.07
    isse
    -0.07
    mobx
    -0.06
     Morrison
    -0.06
     Rou
    -0.06
    eder
    -0.06
    esthesia
    -0.06
    133
    -0.06
    esda
    -0.06
    POSITIVE LOGITS
    aba
    0.07
     Weston
    0.07
    ava
    0.07
    agh
    0.07
    pra
    0.07
    rage
    0.07
     Fem
    0.06
    ad
    0.06
    ãĥ¼ãĥĹ
    0.06
    βα
    0.06
    Activations Density 0.000%

    No Known Activations