© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30827
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with the word "For."

    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
    aly
    -0.07
    ÏįÏĢ
    -0.07
     Erick
    -0.07
    ulg
    -0.06
    ér
    -0.06
    npj
    -0.06
    avery
    -0.06
    orig
    -0.06
    agna
    -0.06
    usb
    -0.06
    POSITIVE LOGITS
     first
    0.14
     Firstly
    0.12
    first
    0.12
     firstly
    0.11
     instance
    0.10
    ãģ¾ãģļ
    0.10
     primero
    0.10
    First
    0.10
     é¦ĸ
    0.09
     First
    0.09
    Activations Density 0.013%

    No Known Activations