© 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. 125058
    Prev
    Next
    INDEX
    Explanations

    elements related to critical reviews and their formatting

    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
    enberg
    -0.07
    loyd
    -0.06
    imer
    -0.06
    oyo
    -0.06
     Tw
    -0.06
    edy
    -0.05
     Mirror
    -0.05
    hee
    -0.05
     symbolic
    -0.05
    ly
    -0.05
    POSITIVE LOGITS
    ampions
    0.07
    ita
    0.07
    ITTE
    0.07
    ADVERTISEMENT
    0.07
    ÙģتÙĩ
    0.07
    견
    0.07
    ÌĤ
    0.07
    ãĥ³ãĤ¯
    0.06
    imde
    0.06
    ëĿ½
    0.06
    Activations Density 0.002%

    No Known Activations