© 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. 60098
    Prev
    Next
    INDEX
    Explanations

    terms related to detention and legal situations

    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
    serter
    -0.08
    iego
    -0.08
    SSION
    -0.08
    endir
    -0.08
    ignum
    -0.08
    hra
    -0.08
    edImage
    -0.08
    RYPT
    -0.08
    iedo
    -0.07
    ilater
    -0.07
    POSITIVE LOGITS
    ta
    0.07
    ter
    0.07
    u
    0.07
    egen
    0.06
    mar
    0.06
    ted
    0.06
     Samurai
    0.06
    esser
    0.06
    ken
    0.06
    ters
    0.06
    Activations Density 0.009%

    No Known Activations