© 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. 83864
    Prev
    Next
    INDEX
    Explanations

    topics related to significant social issues and contemporary events

    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
    =explode
    -0.07
     pione
    -0.07
    ='".$_
    -0.06
    iá»ģn
    -0.06
    iyan
    -0.06
    antar
    -0.06
    åıĬåħ¶
    -0.06
    RoutingModule
    -0.06
     itself
    -0.06
    515
    -0.06
    POSITIVE LOGITS
    -addon
    0.08
    IRT
    0.07
    quip
    0.07
     analogy
    0.07
    ĶåĽŀ
    0.06
    ../../../../
    0.06
    IMIT
    0.06
    nullptr
    0.06
    éģ
    0.06
    OKEN
    0.06
    Activations Density 0.228%

    No Known Activations