© 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. 15-LLAMASCOPE-RES-131K
    6. 89456
    Prev
    Next
    INDEX
    Explanations

    instances of significant numerical values and percentages in discussions about societal issues

    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
     mess
    -0.07
     Mess
    -0.07
    ime
    -0.06
    Mess
    -0.06
     pel
    -0.06
    orge
    -0.06
    aml
    -0.06
    mess
    -0.06
    closure
    -0.06
     Bauer
    -0.06
    POSITIVE LOGITS
     later
    0.11
    以æĿ¥
    0.10
    ä»ĬæĹ¥
    0.10
    Later
    0.09
    later
    0.09
     Later
    0.09
     today
    0.08
     subsequently
    0.08
     aujourd
    0.08
    .Today
    0.08
    Activations Density 0.031%

    No Known Activations