© 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 EvalsExportsinterp-engineNEWAPI 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. 70091
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "others" and variations, indicating comparisons or references to groups apart from the subject

    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
    Ìģt
    -0.09
    stract
    -0.07
    ventus
    -0.07
    LARI
    -0.07
     eigentlich
    -0.07
    vale
    -0.07
    ủa
    -0.07
    еннÑĸ
    -0.07
    SSION
    -0.07
    úsqueda
    -0.07
    POSITIVE LOGITS
     simply
    0.12
     merely
    0.09
     simplement
    0.08
    ,
    0.08
    ones
    0.08
     may
    0.07
     are
    0.07
     naopak
    0.07
     others
    0.07
    åīĩ
    0.07
    Activations Density 0.009%

    No Known Activations