© 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. 75993
    Prev
    Next
    INDEX
    Explanations

    conditional statements that express potential future actions or consequences

    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
     Roose
    -0.07
     panc
    -0.06
    olas
    -0.06
     průbÄĽhu
    -0.06
    arp
    -0.06
    PostBack
    -0.06
    PopupMenu
    -0.06
    ç©
    -0.06
    oa
    -0.06
    854
    -0.06
    POSITIVE LOGITS
    uju
    0.06
     New
    0.06
    áng
    0.06
    eland
    0.06
     Pot
    0.06
    ĸ
    0.06
    nt
    0.06
    uje
    0.06
    jem
    0.06
    äºĪ
    0.06
    Activations Density 0.026%

    No Known Activations