© 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. 85898
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    éģ¸æīĭ
    -0.07
    å²
    -0.07
    pare
    -0.07
    меÑĪ
    -0.07
    .createObject
    -0.06
    ÃŃrk
    -0.06
    Ìģ
    -0.06
     Fabric
    -0.06
    ılıç
    -0.06
    htub
    -0.06
    POSITIVE LOGITS
    iazza
    0.06
     Rig
    0.06
     Vig
    0.06
    nj
    0.06
     pill
    0.06
     Cast
    0.06
    hawks
    0.06
    odes
    0.06
     Sig
    0.06
    лÑĥÑĪ
    0.06
    Activations Density 0.000%

    No Known Activations