© 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. 28223
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is"

    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
    ils
    -0.08
    haven
    -0.08
    haus
    -0.08
    GPC
    -0.07
    Active
    -0.07
    uce
    -0.07
    ÏĦά
    -0.07
    xfff
    -0.07
    ysa
    -0.07
    лÑĥг
    -0.07
    POSITIVE LOGITS
    olation
    0.11
    olated
    0.10
    rael
    0.09
    nt
    0.08
    omorphic
    0.08
    otope
    0.08
    /w
    0.08
    abelle
    0.07
    abella
    0.07
    lington
    0.07
    Activations Density 0.029%

    No Known Activations