© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87233
    Prev
    Next
    INDEX
    Explanations

    themes related to familial separation and reunion

    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
     Byrne
    -0.06
    hti
    -0.06
    aise
    -0.06
    915
    -0.06
     giz
    -0.06
    ifton
    -0.06
     hu
    -0.05
    uchi
    -0.05
    onta
    -0.05
     hyperlink
    -0.05
    POSITIVE LOGITS
    esson
    0.09
    åĬª
    0.07
     Hindered
    0.07
    kest
    0.07
    esan
    0.07
     Face
    0.07
    stav
    0.06
    UDGE
    0.06
     Skype
    0.06
     communication
    0.06
    Activations Density 0.013%

    No Known Activations