© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95287
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to programming and API interactions

    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
     FontStyle
    -0.07
    .MixedReality
    -0.07
    urat
    -0.07
    datatable
    -0.07
    ’ÑıÑĤ
    -0.07
    /null
    -0.06
    .↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    venta
    -0.06
    .↵↵↵↵↵↵↵↵
    -0.06
     Sist
    -0.06
    POSITIVE LOGITS
    ÙĪÙĪ
    0.06
    embali
    0.06
    amba
    0.05
     REALLY
    0.05
    parator
    0.05
    oven
    0.05
    ILLE
    0.05
    clc
    0.05
    orum
    0.05
    ÃŃcÃŃ
    0.05
    Activations Density 0.014%

    No Known Activations