© 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. 17-LLAMASCOPE-RES-131K
    6. 84801
    Prev
    Next
    INDEX
    Explanations

    structured numerical data and punctuation in financial or statistical contexts

    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
     tower
    -0.07
     Woodward
    -0.06
    éİ®
    -0.06
     Tower
    -0.06
    testdata
    -0.06
     hâl
    -0.06
    ij¸
    -0.06
    Calibri
    -0.06
    illin
    -0.06
    имÑĥ
    -0.06
    POSITIVE LOGITS
    isContained
    0.06
    -INFRINGEMENT
    0.06
    ANJI
    0.06
    actionDate
    0.06
     Bannon
    0.06
    idor
    0.06
    itled
    0.06
    reinterpret
    0.06
    æŃ
    0.05
    _IMPL
    0.05
    Activations Density 0.003%

    No Known Activations