© 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. 2983
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate product performance and longevity

    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
    FLT
    -0.07
    ãĥ¼ãĤ¯
    -0.07
    iston
    -0.07
    hung
    -0.07
    583
    -0.07
    ãģŁãģĦ
    -0.07
    Formatting
    -0.06
    tones
    -0.06
    Informe
    -0.06
    783
    -0.06
    POSITIVE LOGITS
     Dur
    0.08
    Dur
    0.07
    buat
    0.07
     resistance
    0.07
    GH
    0.07
     durability
    0.06
     Resistance
    0.06
     Scholar
    0.06
    antas
    0.06
    .zh
    0.06
    Activations Density 0.001%

    No Known Activations