© 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. 4701
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and their contexts within the text

    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
    -0.07
     opposite
    -0.06
     scatter
    -0.06
     v
    -0.06
    adj
    -0.05
     c
    -0.05
    alan
    -0.05
    irie
    -0.05
     variable
    -0.05
     formal
    -0.05
    POSITIVE LOGITS
    (AP
    0.11
    istrat
    0.09
    nga
    0.08
    afone
    0.08
    .ng
    0.08
    AP
    0.08
     AppleWebKit
    0.08
    cete
    0.08
    .scalablytyped
    0.07
    ега
    0.07
    Activations Density 0.003%

    No Known Activations