© 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. 129329
    Prev
    Next
    INDEX
    Explanations

    references to awards and recognition events

    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
    IRECT
    -0.07
    conciliation
    -0.07
    uta
    -0.07
    olla
    -0.07
     helicopt
    -0.07
    ubat
    -0.07
    edImage
    -0.07
    tlement
    -0.07
    apolis
    -0.07
    asses
    -0.07
    POSITIVE LOGITS
     awards
    0.07
     award
    0.07
    0.07
     service
    0.07
     deserving
    0.07
     awarded
    0.06
     indiv
    0.06
     Service
    0.06
    ispiel
    0.06
     exceptional
    0.06
    Activations Density 0.040%

    No Known Activations