© 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. 15-LLAMASCOPE-RES-131K
    11. 89553
    Prev
    Next
    INDEX
    Explanations

    words indicating irrational behavior or unpredictability

    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
    íĥĪ
    -0.06
    ishing
    -0.06
    reate
    -0.06
    ainen
    -0.06
    akens
    -0.06
     Vog
    -0.06
    å¯
    -0.06
    اض
    -0.06
    åł´
    -0.06
    arium
    -0.06
    POSITIVE LOGITS
    imes
    0.07
    ovsky
    0.07
    OMPI
    0.07
    kB
    0.06
    ivy
    0.06
     %[
    0.06
     Richie
    0.06
    ief
    0.06
     Telefon
    0.06
    asto
    0.06
    Activations Density 0.000%

    No Known Activations