© 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. 126169
    Prev
    Next
    INDEX
    Explanations

    the word "now" in various contexts

    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
    unate
    -0.07
    itest
    -0.07
    cker
    -0.07
    ondheim
    -0.07
    ãģłãģª
    -0.07
    later
    -0.07
    onis
    -0.07
     later
    -0.06
    wire
    -0.06
    licity
    -0.06
    POSITIVE LOGITS
    adays
    0.13
    withstanding
    0.12
    days
    0.10
    here
    0.10
    aday
    0.10
    ise
    0.09
    ledge
    0.09
     Äijây
    0.08
    ruz
    0.08
    HERE
    0.08
    Activations Density 0.065%

    No Known Activations