© 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. 17-LLAMASCOPE-RES-131K
    11. 87439
    Prev
    Next
    INDEX
    Explanations

    references to music that addresses personal struggles or encourages emotional responses

    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
     hub
    -0.07
     ro
    -0.06
    iew
    -0.06
     perish
    -0.06
     exhaust
    -0.06
     Glad
    -0.06
     addict
    -0.06
    ıydı
    -0.06
     resp
    -0.05
    hub
    -0.05
    POSITIVE LOGITS
     Mood
    0.08
    Listeners
    0.07
     anth
    0.07
    anth
    0.07
    etÃŃ
    0.07
     mood
    0.07
     listeners
    0.07
     listener
    0.07
    vell
    0.07
    uzzi
    0.07
    Activations Density 0.028%

    No Known Activations