© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92830
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when" and related temporal modifiers

    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
    agini
    -0.08
    à¹Ħว
    -0.08
    rens
    -0.07
    خراج
    -0.07
    ÑĢоÑĦ
    -0.07
    selectedIndex
    -0.07
    abcdefgh
    -0.07
    мага
    -0.07
    éru
    -0.07
    VERRIDE
    -0.07
    POSITIVE LOGITS
    inky
    0.06
     Sink
    0.06
     Lia
    0.06
    Sink
    0.05
    sink
    0.05
     FRA
    0.05
    cz
    0.05
    Reach
    0.05
    ök
    0.05
    /dat
    0.05
    Activations Density 0.003%

    No Known Activations