© 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. 72301
    Prev
    Next
    INDEX
    Explanations

    expressions of audience engagement and emotional involvement with artistic works

    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
    ãģ¬
    -0.07
    innie
    -0.07
    759
    -0.07
    872
    -0.06
     Saved
    -0.06
    992
    -0.06
    inta
    -0.06
     saved
    -0.06
    aking
    -0.06
    239
    -0.06
    POSITIVE LOGITS
     attention
    0.09
    attention
    0.08
     внимание
    0.08
     engagement
    0.08
     interest
    0.08
     Peaks
    0.08
    .scalar
    0.08
     capt
    0.08
    -eng
    0.07
    hook
    0.07
    Activations Density 0.024%

    No Known Activations