© 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. 92658
    Prev
    Next
    INDEX
    Explanations

    instances of the word "subscribe"

    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
    oller
    -0.06
     congr
    -0.06
    otty
    -0.06
    .IM
    -0.06
    ective
    -0.06
    odie
    -0.06
    .Dependency
    -0.06
     sut
    -0.06
    plib
    -0.05
    810
    -0.05
    POSITIVE LOGITS
     ÐľÐ¸Ðº
    0.07
    ancia
    0.07
    skins
    0.06
    ancial
    0.06
    LR
    0.06
    isclosed
    0.06
    ancias
    0.06
    gx
    0.06
    chein
    0.06
    ughter
    0.06
    Activations Density 0.002%

    No Known Activations