© 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. 69471
    Prev
    Next
    INDEX
    Explanations

    pronouns and expressions of emotional engagement

    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
    cly
    -0.08
    rais
    -0.07
    macı
    -0.07
    baÅŁ
    -0.07
    .Ordinal
    -0.07
    dete
    -0.07
    orna
    -0.07
    oley
    -0.07
    BaseContext
    -0.07
    cete
    -0.07
    POSITIVE LOGITS
     ever
    0.11
     than
    0.08
    aviest
    0.08
    ever
    0.07
    eping
    0.07
     EVER
    0.07
    irt
    0.07
    -ever
    0.06
     Ever
    0.06
     Donovan
    0.06
    Activations Density 0.009%

    No Known Activations