© 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. 87009
    Prev
    Next
    INDEX
    Explanations

    relationships and familial connections among characters

    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
    urum
    -0.07
    ør
    -0.07
    imbus
    -0.06
     ëķĮ문
    -0.06
    isen
    -0.06
     superClass
    -0.06
    amp
    -0.06
    utilus
    -0.06
     factors
    -0.06
    akah
    -0.06
    POSITIVE LOGITS
     their
    0.08
    ritch
    0.08
    their
    0.07
     loro
    0.07
     leurs
    0.07
     иÑħ
    0.07
     nackt
    0.07
    Their
    0.07
    ayne
    0.07
    ycz
    0.06
    Activations Density 0.018%

    No Known Activations