© 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. 106283
    Prev
    Next
    INDEX
    Explanations

    phrases related to building and strengthening connections or relationships

    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
    aupt
    -0.07
    opensource
    -0.06
    arding
    -0.06
    strand
    -0.06
    ndo
    -0.06
    igham
    -0.06
    umbing
    -0.06
    nd
    -0.06
    orus
    -0.06
     Narc
    -0.06
    POSITIVE LOGITS
    adox
    0.07
    çe
    0.07
    chner
    0.06
    RGBA
    0.06
    ibal
    0.06
     sona
    0.06
    alet
    0.06
    TPL
    0.06
     expertise
    0.06
    bec
    0.06
    Activations Density 0.017%

    No Known Activations