© 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. 15609
    Prev
    Next
    INDEX
    Explanations

    actions and commands related to user interactions in a software or application context

    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
    _UNIFORM
    -0.07
    hic
    -0.07
    frau
    -0.07
    @qq
    -0.07
    immers
    -0.07
    arkan
    -0.07
    ercul
    -0.07
     treff
    -0.06
     hảo
    -0.06
     Pod
    -0.06
    POSITIVE LOGITS
     twice
    0.08
     button
    0.07
    æĮīéĴ®
    0.06
    SPATH
    0.06
    atin
    0.06
    éĴ®
    0.06
    nowled
    0.06
     ÑĩÑĤобÑĭ
    0.06
    OK
    0.06
    446
    0.06
    Activations Density 0.004%

    No Known Activations