© 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. 79894
    Prev
    Next
    INDEX
    Explanations

    the usage of the word "we" and related expressions indicating group participation or collaboration

    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
    мени
    -0.06
    rud
    -0.06
    verte
    -0.06
     therefore
    -0.06
    avez
    -0.06
    levant
    -0.06
    oader
    -0.06
     Belly
    -0.06
     eigenen
    -0.06
     sprink
    -0.06
    POSITIVE LOGITS
     studies
    0.06
    hetto
    0.06
    ishop
    0.06
    ASTE
    0.06
    ERGE
    0.06
    AVIS
    0.06
     remot
    0.06
    ãĥĥãĤ¯ãĤ¹
    0.06
    Æ°á»Ŀng
    0.06
    ieder
    0.06
    Activations Density 0.070%

    No Known Activations