© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 79079
    Prev
    Next
    INDEX
    Explanations

    references to thoroughness and completeness in reports or evaluations

    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
    iversal
    -0.08
    ItemAt
    -0.08
    TON
    -0.08
    æĮ¯ãĤĬ
    -0.08
    ton
    -0.08
    blr
    -0.07
    aN
    -0.07
    /cms
    -0.07
    Qualifier
    -0.07
    ARING
    -0.07
    POSITIVE LOGITS
     relevant
    0.09
     aspects
    0.08
     necessary
    0.07
     rele
    0.07
     available
    0.06
     possible
    0.06
     aspect
    0.06
    nerg
    0.06
     stakeholders
    0.06
     details
    0.06
    Activations Density 0.024%

    No Known Activations