© 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. 56042
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate adherence or obedience to guidelines or examples

    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
     migrationBuilder
    -0.07
    bil
    -0.06
     Altern
    -0.06
    altern
    -0.06
    Disposed
    -0.06
    θεν
    -0.06
    chine
    -0.06
    iÅŁi
    -0.06
    ood
    -0.06
    ATS
    -0.06
    POSITIVE LOGITS
     footsteps
    0.08
     trend
    0.08
     followed
    0.08
    -follow
    0.07
     adopt
    0.07
     trends
    0.07
     preced
    0.07
    (QStringLiteral
    0.07
    follow
    0.07
    inters
    0.07
    Activations Density 0.013%

    No Known Activations