© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88058
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with personal introspection or emotions

    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
    vie
    -0.07
     dev
    -0.06
     sire
    -0.06
     within
    -0.06
     graz
    -0.06
     Mil
    -0.06
    crate
    -0.06
     fashion
    -0.06
     Graz
    -0.06
     mil
    -0.06
    POSITIVE LOGITS
    Ø·
    0.07
    æŁ
    0.07
    anim
    0.07
    оÑİ
    0.07
    _PUR
    0.07
    ิà¸Ļà¸Ħ
    0.06
    186
    0.06
     Platform
    0.06
    enames
    0.06
    _DBG
    0.06
    Activations Density 0.002%

    No Known Activations