© 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. 17-LLAMASCOPE-RES-131K
    11. 124771
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationship dynamics and social interactions

    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
    ulo
    -0.07
    ¹Ħ
    -0.07
    ulan
    -0.07
     곧
    -0.07
    .medium
    -0.07
    ymi
    -0.07
    etty
    -0.07
    anto
    -0.07
    ayd
    -0.07
     medium
    -0.07
    POSITIVE LOGITS
     twice
    0.11
     younger
    0.11
     older
    0.10
     Twice
    0.09
     age
    0.09
    æ¯Ķ
    0.09
     elder
    0.08
    åĢį
    0.08
    olders
    0.08
     äl
    0.07
    Activations Density 0.084%

    No Known Activations