© 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 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. 76536
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions, particularly those related to technology and engineering

    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
    nett
    -0.07
    ieres
    -0.06
    rl
    -0.06
    олеÑĤ
    -0.06
    ston
    -0.06
     ud
    -0.06
    opard
    -0.06
     Niet
    -0.05
     Ini
    -0.05
    illac
    -0.05
    POSITIVE LOGITS
    .Designer
    0.08
    пÑĢиклад
    0.07
    kek
    0.07
    sun
    0.07
    /engine
    0.07
    iT
    0.07
    åģı
    0.06
    bib
    0.06
    aktu
    0.06
    rtl
    0.06
    Activations Density 0.009%

    No Known Activations