© 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. 95000
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to emotions and personal conflicts

    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
    .scalablytyped
    -0.08
    ä½
    -0.08
    /goto
    -0.08
    ìŀ¡ëĭ´
    -0.08
    ropa
    -0.07
    ãĥ©ãĤ¯
    -0.07
    etine
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    chalk
    -0.07
    _Tis
    -0.07
    POSITIVE LOGITS
     B
    0.06
     M
    0.06
     Cro
    0.06
    dr
    0.06
     Harris
    0.06
    fic
    0.06
     Gram
    0.06
     Gregory
    0.06
     sembl
    0.06
     everyone
    0.06
    Activations Density 0.023%

    No Known Activations