© 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. 9-LLAMASCOPE-RES-131K
    11. 96352
    Prev
    Next
    INDEX
    Explanations

    concepts related to achievements and progress in a gamified context

    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
    ãģıãĤī
    -0.06
     specimen
    -0.06
    /tos
    -0.06
     ~
    -0.06
     Zug
    -0.05
    knife
    -0.05
     cycl
    -0.05
     Mund
    -0.05
     cells
    -0.05
    ëĮĢíĸī
    -0.05
    POSITIVE LOGITS
     Rouge
    0.08
    ubat
    0.07
     Targets
    0.07
    pressor
    0.07
     Fet
    0.07
    atta
    0.07
    oks
    0.07
    hk
    0.07
    .raise
    0.07
     Target
    0.07
    Activations Density 0.028%

    No Known Activations