© 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. 88792
    Prev
    Next
    INDEX
    Explanations

    terms related to grant writing and documentation processes

    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
     revelations
    -0.06
    Agents
    -0.06
    ula
    -0.06
    /bower
    -0.06
    Ñĥла
    -0.06
     confessed
    -0.05
     sinc
    -0.05
     voc
    -0.05
    OWL
    -0.05
    916
    -0.05
    POSITIVE LOGITS
     reports
    0.08
     Qed
    0.08
     prepare
    0.08
     prepares
    0.08
     draft
    0.08
     Prepare
    0.07
     гоÑĤов
    0.07
     report
    0.07
    prepare
    0.07
    ynamo
    0.07
    Activations Density 0.027%

    No Known Activations