© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56112
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and issues related to freedom of speech and assembly

    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
     Cycle
    -0.07
     cycle
    -0.06
     Complex
    -0.06
    алог
    -0.06
     AMA
    -0.06
    éĨ
    -0.06
    lore
    -0.06
     stolen
    -0.06
     val
    -0.06
    ALK
    -0.05
    POSITIVE LOGITS
    spa
    0.08
    Ùħبر
    0.07
    mary
    0.07
     sed
    0.07
    plusplus
    0.07
    ãĤįãģĨ
    0.07
     lib
    0.07
     Fell
    0.07
    actus
    0.07
    postal
    0.07
    Activations Density 0.141%

    No Known Activations