© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 55530
    Prev
    Next
    INDEX
    Explanations

    measurements and spatial relationships

    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
    isma
    -0.09
    elog
    -0.08
    ibold
    -0.08
    isko
    -0.07
    .synthetic
    -0.07
    erable
    -0.07
     Erotische
    -0.07
    ewidth
    -0.07
    itto
    -0.07
    elry
    -0.07
    POSITIVE LOGITS
     tip
    0.07
    ivil
    0.05
     Civil
    0.05
     civil
    0.05
     Tro
    0.05
    ilar
    0.05
     Living
    0.05
    andas
    0.05
     Catal
    0.05
     fren
    0.05
    Activations Density 0.005%

    No Known Activations