© 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. 83532
    Prev
    Next
    INDEX
    Explanations

    the word "so" in various contexts, indicating a focus on conversational or rhetorical phrasing

    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
    utin
    -0.07
    еÑĢÑĪ
    -0.06
    ercul
    -0.06
    phon
    -0.06
    Ø®
    -0.06
    FFE
    -0.06
    пÑĢимеÑĢ
    -0.06
    bsite
    -0.06
    âĢŀV
    -0.06
    vice
    -0.06
    POSITIVE LOGITS
     then
    0.08
     thì
    0.07
    ,
    0.07
    çļĦè¯Ŀ
    0.07
    ifiable
    0.06
     THEN
    0.06
    then
    0.06
     Then
    0.06
    :↵
    0.06
    Then
    0.06
    Activations Density 0.003%

    No Known Activations