© 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. 16428
    Prev
    Next
    INDEX
    Explanations

    expressions relating to parental experiences and reflections

    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
    ater
    -0.07
    engin
    -0.07
    atas
    -0.06
     Zot
    -0.06
     Great
    -0.06
    holm
    -0.06
    ross
    -0.06
    sn
    -0.06
     McKay
    -0.06
     garant
    -0.06
    POSITIVE LOGITS
    Į¨
    0.07
    วล
    0.07
    tsx
    0.07
    unami
    0.06
    ceptar
    0.06
    oningen
    0.06
    ापन
    0.06
    ánu
    0.06
    indi
    0.06
    ornings
    0.06
    Activations Density 0.016%

    No Known Activations