© 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. 77119
    Prev
    Next
    INDEX
    Explanations

    themes related to family and emotional connections

    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
    éné
    -0.10
    ureau
    -0.09
    elper
    -0.08
    pll
    -0.08
    enne
    -0.07
    yal
    -0.07
    ä»ĭ
    -0.07
    ãĤīãģĽ
    -0.07
    plode
    -0.07
    ëł´
    -0.07
    POSITIVE LOGITS
     missing
    0.09
     lost
    0.08
     Missing
    0.08
     reun
    0.07
    missing
    0.06
     former
    0.06
     original
    0.06
     proper
    0.06
     natural
    0.06
     identity
    0.06
    Activations Density 0.019%

    No Known Activations