© 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. 17-LLAMASCOPE-RES-131K
    11. 59643
    Prev
    Next
    INDEX
    Explanations

    references to structured data formats, particularly JSON

    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
    sp
    -0.06
    &C
    -0.06
    ede
    -0.06
     g
    -0.06
    if
    -0.06
    bul
    -0.05
    jb
    -0.05
    aran
    -0.05
     âĢ¦
    -0.05
     drawing
    -0.05
    POSITIVE LOGITS
     fitte
    0.08
    .cloudflare
    0.07
    ornings
    0.07
    μιÏĥ
    0.07
    ("{\"
    0.07
    ouri
    0.07
    semblies
    0.07
    vine
    0.07
    \Migrations
    0.07
    ipelines
    0.07
    Activations Density 0.022%

    No Known Activations