© 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. 556
    Prev
    Next
    INDEX
    Explanations

    numeric values and their relationships in a text

    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
    erno
    -0.07
    omon
    -0.07
    aille
    -0.07
    ioni
    -0.07
    604
    -0.06
    lica
    -0.06
    اÙĦا
    -0.06
    liqu
    -0.06
    ninger
    -0.06
    antee
    -0.06
    POSITIVE LOGITS
    rung
    0.08
    ade
    0.07
    TRS
    0.06
    chter
    0.06
    Äįer
    0.06
    CellValue
    0.06
    850
    0.06
    SCO
    0.06
    eff
    0.06
    iage
    0.06
    Activations Density 0.013%

    No Known Activations