© 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. 15-LLAMASCOPE-RES-131K
    11. 103862
    Prev
    Next
    INDEX
    Explanations

    occurrences of document type declarations in HTML

    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
    جاد
    -0.07
    berg
    -0.06
    ogle
    -0.06
     ãĤ¢ãĤ¤
    -0.06
    ãģĺ
    -0.06
    Ø©
    -0.06
    pires
    -0.06
    rier
    -0.06
    side
    -0.06
     èŃ
    -0.06
    POSITIVE LOGITS
    idders
    0.07
    abbo
    0.07
    enan
    0.06
    inode
    0.06
    inqu
    0.06
    Fight
    0.06
     Shack
    0.06
    ignet
    0.06
    istrovstvÃŃ
    0.06
     Nolan
    0.06
    Activations Density 0.000%

    No Known Activations