© 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. 119166
    Prev
    Next
    INDEX
    Explanations

    references to technology companies and their products or innovations

    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
    arsity
    -0.07
    akis
    -0.07
    isz
    -0.07
    ERP
    -0.07
    DMA
    -0.07
    è¶
    -0.06
    ovo
    -0.06
    ì¶Ķì²ľ
    -0.06
    大åħ¨
    -0.06
    é±
    -0.06
    POSITIVE LOGITS
     sublicense
    0.07
    ÄĻd
    0.06
     progress
    0.06
     mat
    0.06
     scaled
    0.06
    á»ģ
    0.06
     tick
    0.06
     early
    0.06
     test
    0.06
     funding
    0.06
    Activations Density 0.012%

    No Known Activations