© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61441
    Prev
    Next
    INDEX
    Explanations

    questions and conditional statements related to programming and mathematical concepts

    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
    azo
    -0.06
    rade
    -0.06
    exion
    -0.06
    imd
    -0.06
    emer
    -0.06
    elt
    -0.06
    esso
    -0.06
    rnÄĽ
    -0.06
    анÑĮ
    -0.05
    ·
    -0.05
    POSITIVE LOGITS
     then
    0.26
    then
    0.23
     Then
    0.22
     entonces
    0.21
    Then
    0.20
     então
    0.19
     thì
    0.19
     THEN
    0.18
    	then
    0.18
     ÑĤогда
    0.18
    Activations Density 0.127%

    No Known Activations