© 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. 9-LLAMASCOPE-RES-131K
    11. 97798
    Prev
    Next
    INDEX
    Explanations

    references to precious metals and jewelry

    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
    etch
    -0.07
    edl
    -0.06
    ational
    -0.06
     Sab
    -0.06
    ijo
    -0.06
    erra
    -0.06
     elevation
    -0.06
    obil
    -0.05
     industrial
    -0.05
     Doch
    -0.05
    POSITIVE LOGITS
    haft
    0.08
     thuáºŃt
    0.08
    arias
    0.07
     kli
    0.07
    ector
    0.07
    ERGY
    0.07
    ÛĮز
    0.07
    лÑİд
    0.06
    Ñħи
    0.06
    ansas
    0.06
    Activations Density 0.009%

    No Known Activations