© 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. 4879
    Prev
    Next
    INDEX
    Explanations

    word variations and formations linked to actions or processes happening in real-time or that suggest transformation

    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
    efined
    -0.08
    tır
    -0.07
    tür
    -0.07
    ytut
    -0.07
    guest
    -0.07
    culate
    -0.07
    親
    -0.07
    Guest
    -0.07
    anela
    -0.07
    hev
    -0.07
    POSITIVE LOGITS
    atre
    0.10
    etheless
    0.09
    gether
    0.09
    adays
    0.09
    bsites
    0.08
    .com
    0.07
    .net
    0.07
    .org
    0.07
    xiety
    0.07
    nger
    0.07
    Activations Density 0.106%

    No Known Activations