© 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. 123995
    Prev
    Next
    INDEX
    Explanations

    concepts related to communication and interpersonal 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
     maybe
    -0.06
    -0.06
     Suddenly
    -0.06
    359
    -0.06
     patience
    -0.05
    VOKE
    -0.05
     remaining
    -0.05
    FA
    -0.05
    f
    -0.05
    l
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.10
    CommandEvent
    0.08
    ãģĸ
    0.08
    =log
    0.08
    uards
    0.07
    rocessing
    0.07
    $action
    0.07
    епÑĤи
    0.07
    ACTION
    0.07
    _Tis
    0.07
    Activations Density 0.013%

    No Known Activations