© 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. 60175
    Prev
    Next
    INDEX
    Explanations

    strings related to time zones and timestamps

    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
    achten
    -0.07
    lij
    -0.06
     Petty
    -0.06
    irus
    -0.06
    bench
    -0.06
    lun
    -0.06
    ä½ĵèĤ²
    -0.06
    pron
    -0.06
     Bench
    -0.06
    itele
    -0.06
    POSITIVE LOGITS
     Sesso
    0.07
    TOOLS
    0.07
    ibase
    0.06
    toFloat
    0.06
    .Scroll
    0.06
    /Peak
    0.06
    oya
    0.06
    ernel
    0.06
     Zack
    0.06
    azio
    0.06
    Activations Density 0.001%

    No Known Activations