© 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 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. 85605
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" and variations associated with it, particularly in phrases that convey relationships or ownership

    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
    efa
    -0.07
    enez
    -0.07
    inus
    -0.07
    (using
    -0.07
    eno
    -0.07
    umer
    -0.06
    uyá»ĩt
    -0.06
     intra
    -0.06
     baz
    -0.06
     roc
    -0.06
    POSITIVE LOGITS
    igs
    0.06
    502
    0.06
    igr
    0.06
     where
    0.06
    icit
    0.06
    omain
    0.06
    illet
    0.06
    ÑģкоÑĢ
    0.06
     tit
    0.06
    elik
    0.06
    Activations Density 0.028%

    No Known Activations