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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75371
    Prev
    Next
    INDEX
    Explanations

    construction and descriptions of significant events or actions

    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
    λÏī
    -0.07
    elters
    -0.07
    Ñĥжд
    -0.07
    ABEL
    -0.07
    оÑĢоÑĤ
    -0.06
    ابر
    -0.06
     eventual
    -0.06
    rovers
    -0.06
    akest
    -0.06
    eid
    -0.06
    POSITIVE LOGITS
    .asp
    0.07
     hadn
    0.07
     earlier
    0.07
     бÑĭ
    0.07
    would
    0.07
    639
    0.06
    nt
    0.06
     ÑĢанÑĮÑĪе
    0.06
     habÃŃa
    0.06
    nts
    0.06
    Activations Density 0.147%

    No Known Activations