© 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. 130129
    Prev
    Next
    INDEX
    Explanations

    action verbs associated with formal agreements or events

    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
     Truy
    -0.08
    ellig
    -0.07
    itational
    -0.07
    eniable
    -0.07
     Mish
    -0.07
     à¤ħपर
    -0.06
    lea
    -0.06
    æĦıä¹ī
    -0.06
    elson
    -0.06
    ivas
    -0.06
    POSITIVE LOGITS
    çļĦæĺ¯
    0.08
     because
    0.07
     especially
    0.07
    inski
    0.07
    411
    0.07
     without
    0.06
     after
    0.06
    porte
    0.06
     particularly
    0.06
    nant
    0.06
    Activations Density 0.083%

    No Known Activations