© 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. 40442
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals named Ken

    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
    oling
    -0.07
     tá»ij
    -0.07
    encer
    -0.07
    indexes
    -0.07
    erot
    -0.07
    illery
    -0.07
    eyn
    -0.07
    cela
    -0.06
    itesse
    -0.06
    lando
    -0.06
    POSITIVE LOGITS
    yon
    0.09
    zie
    0.08
    ya
    0.08
    worthy
    0.07
    zik
    0.07
    igma
    0.07
    yal
    0.06
    mare
    0.06
    485
    0.06
    ran
    0.06
    Activations Density 0.011%

    No Known Activations