© 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. 84812
    Prev
    Next
    INDEX
    Explanations

    references to a particular programming framework or library

    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
    bet
    -0.06
    ame
    -0.06
    ftware
    -0.06
     reconc
    -0.05
     dak
    -0.05
    ären
    -0.05
    ut
    -0.05
     reconciliation
    -0.05
    aille
    -0.05
    ary
    -0.05
    POSITIVE LOGITS
    ãİ
    0.08
    _EOL
    0.07
    chied
    0.07
    (#)
    0.07
    inality
    0.07
    inal
    0.07
    Äł
    0.07
     Ãĸzel
    0.07
    #{@
    0.07
    /XML
    0.07
    Activations Density 0.000%

    No Known Activations