© 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. 62208
    Prev
    Next
    INDEX
    Explanations

    technical details related to scientific experiments

    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
     oss
    -0.07
    uzz
    -0.06
     scand
    -0.06
    adge
    -0.06
    orra
    -0.06
     jur
    -0.06
    mey
    -0.06
     nou
    -0.05
    jur
    -0.05
    .Port
    -0.05
    POSITIVE LOGITS
    ãĥĭãĥ¼
    0.07
    aturated
    0.07
    Unused
    0.07
    ãĤ¤ãĤ¯
    0.07
    MBED
    0.07
    HEME
    0.06
    åĿı
    0.06
    _macro
    0.06
     Choi
    0.06
    recision
    0.06
    Activations Density 0.004%

    No Known Activations