© 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. 5-LLAMASCOPE-RES-131K
    11. 126836
    Prev
    Next
    INDEX
    Explanations

    references to small businesses or family-owned establishments

    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
    kl
    -0.06
     dou
    -0.06
    353
    -0.06
    æĤ
    -0.06
    perf
    -0.06
    828
    -0.06
    297
    -0.06
     Alv
    -0.05
    903
    -0.05
    774
    -0.05
    POSITIVE LOGITS
     Affairs
    0.07
     kabil
    0.07
    heim
    0.06
    external
    0.06
    External
    0.06
    acter
    0.06
     <!--[
    0.06
    cock
    0.06
    iless
    0.06
    acker
    0.06
    Activations Density 0.001%

    No Known Activations