© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94469
    Prev
    Next
    INDEX
    Explanations

    themes of loss and grief intertwined with support and memory

    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
    enal
    -0.06
    ervo
    -0.06
     Means
    -0.06
    ENA
    -0.06
    ens
    -0.06
    onian
    -0.06
     yourselves
    -0.06
    igi
    -0.06
    hd
    -0.06
    iais
    -0.06
    POSITIVE LOGITS
     loss
    0.10
     deceased
    0.09
    loss
    0.09
     murdered
    0.08
     killed
    0.08
     dead
    0.08
     Loss
    0.07
     Killed
    0.07
     bere
    0.07
    bere
    0.07
    Activations Density 0.049%

    No Known Activations