© 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. 87602
    Prev
    Next
    INDEX
    Explanations

    terms related to COVID-19 and public health information

    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
     zde
    -0.06
    ãĥ¼ãĥĢ
    -0.06
     bias
    -0.06
     Hung
    -0.06
    IELD
    -0.06
    gist
    -0.05
     similarly
    -0.05
    cord
    -0.05
     Nico
    -0.05
    bcd
    -0.05
    POSITIVE LOGITS
    .jpg
    0.13
    .pdf
    0.12
    .png
    0.10
    .JPG
    0.10
    .xlsx
    0.10
    .doc
    0.09
    .PNG
    0.09
    .jpeg
    0.09
    .xls
    0.08
    .rar
    0.08
    Activations Density 0.051%

    No Known Activations