© 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. 28715
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structures related to data manipulation or programming logic

    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
    bour
    -0.09
    prite
    -0.07
     queryInterface
    -0.07
    amera
    -0.07
     Trophy
    -0.07
    Ïģιν
    -0.07
    ablish
    -0.07
    θη
    -0.07
    plusplus
    -0.06
    worthy
    -0.06
    POSITIVE LOGITS
    ed
    0.07
    ust
    0.07
    ustom
    0.06
    aes
    0.06
    ade
    0.06
    rypto
    0.06
    mel
    0.06
    .ix
    0.06
     ar
    0.06
     equ
    0.06
    Activations Density 0.031%

    No Known Activations