© 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. 57925
    Prev
    Next
    INDEX
    Explanations

    dialogue or quotations within the text

    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
    Ñĥма
    -0.06
    .scalablytyped
    -0.06
    lich
    -0.06
    æ³£
    -0.06
     vaguely
    -0.06
    ênh
    -0.06
    udo
    -0.06
    diler
    -0.06
    çĦ¦
    -0.06
     thá»ķ
    -0.06
    POSITIVE LOGITS
     joke
    0.11
     jokes
    0.10
    ï¼Īç¬ij
    0.09
     joking
    0.08
     joked
    0.08
     mock
    0.08
     fun
    0.07
    Äħż
    0.07
     jest
    0.07
     tongue
    0.07
    Activations Density 0.047%

    No Known Activations