© 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. 56238
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to machinery or systems

    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
    .scalablytyped
    -0.09
    ovel
    -0.08
    lage
    -0.08
    edenÃŃ
    -0.08
    abet
    -0.08
    ACHE
    -0.08
    patches
    -0.07
    ouse
    -0.07
    acen
    -0.07
    izo
    -0.07
    POSITIVE LOGITS
    lays
    0.05
     spare
    0.05
     certain
    0.05
     service
    0.05
    821
    0.05
     contained
    0.05
     Bac
    0.05
    ↵
    0.05
     Society
    0.05
     accum
    0.05
    Activations Density 0.001%

    No Known Activations