© 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. 22-LLAMASCOPE-RES-131K
    11. 3651
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    οÏħλ
    -0.07
    cono
    -0.07
    /cgi
    -0.07
    alars
    -0.07
    .populate
    -0.07
    uco
    -0.06
    tent
    -0.06
    fak
    -0.06
    .hm
    -0.06
    plat
    -0.06
    POSITIVE LOGITS
    ÑĤин
    0.06
    avan
    0.05
    à¹ģล
    0.05
    USES
    0.05
     Hue
    0.05
    zelf
    0.05
    >tag
    0.05
    ICODE
    0.05
     Unified
    0.05
     Trib
    0.05
    Activations Density 0.004%

    No Known Activations