© 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. 39939
    Prev
    Next
    INDEX
    Explanations

    instances of qualifying statements or conditions that enhance descriptions

    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
    anz
    -0.07
    swers
    -0.07
    abbo
    -0.06
    ubits
    -0.06
    åºķ
    -0.06
     shut
    -0.06
    uman
    -0.06
     thải
    -0.06
    ãĤĴãģĭ
    -0.06
    objects
    -0.06
    POSITIVE LOGITS
     partly
    0.06
     attribute
    0.06
     reflect
    0.06
     surprise
    0.06
    åĩºçīĪ社
    0.06
    argin
    0.06
    izona
    0.06
    apes
    0.06
    uria
    0.06
     trait
    0.06
    Activations Density 0.031%

    No Known Activations