© 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. 29195
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors used in lists and phrases

    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
    621
    -0.06
     ones
    -0.06
    ¾
    -0.06
    iams
    -0.05
    plug
    -0.05
    aux
    -0.05
    595
    -0.05
    531
    -0.05
    623
    -0.05
    X
    -0.05
    POSITIVE LOGITS
     accompanying
    0.10
     associated
    0.09
    ноÑģÑĤ
    0.09
    reas
    0.08
    associated
    0.08
    çĭIJ
    0.08
    orra
    0.08
    kili
    0.08
    kova
    0.07
    urma
    0.07
    Activations Density 0.056%

    No Known Activations