© 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. 59262
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their familial 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
    always
    -0.09
     always
    -0.08
    Always
    -0.08
     toujours
    -0.08
     sempre
    -0.08
    ueur
    -0.08
    uchs
    -0.08
     вÑģегда
    -0.08
    ADDE
    -0.07
     tends
    -0.07
    POSITIVE LOGITS
     probably
    0.09
    probably
    0.07
     lucky
    0.07
     Probably
    0.07
     example
    0.06
     prob
    0.06
     fortunate
    0.06
    еÑħ
    0.06
     chosen
    0.06
     unlikely
    0.06
    Activations Density 0.045%

    No Known Activations