© 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. 70612
    Prev
    Next
    INDEX
    Explanations

    special characters or encoded text that may represent a certain format or data type

    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
     dil
    -0.07
    nila
    -0.06
    .HttpContext
    -0.06
    erte
    -0.06
    ake
    -0.06
    oka
    -0.06
    ijken
    -0.06
    hai
    -0.06
    icho
    -0.06
     subordinate
    -0.06
    POSITIVE LOGITS
    rious
    0.07
    ãĤ¦ãĥĪ
    0.07
    911
    0.07
    egis
    0.07
    utzer
    0.07
     기íĥĢ
    0.07
    411
    0.06
    iom
    0.06
    leigh
    0.06
    湯
    0.06
    Activations Density 0.000%

    No Known Activations