© 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. 94734
    Prev
    Next
    INDEX
    Explanations

    actions and emotions experienced during creative processes or performances

    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
     finish
    -0.07
     continue
    -0.07
     twice
    -0.07
     continuing
    -0.07
    Continue
    -0.07
     spike
    -0.07
    acha
    -0.07
    amat
    -0.06
    continue
    -0.06
     continuation
    -0.06
    POSITIVE LOGITS
     increasingly
    0.09
     began
    0.09
     dần
    0.09
     begins
    0.09
     gradually
    0.08
     zaÄįal
    0.08
     Begins
    0.08
     begun
    0.08
     slowly
    0.08
     Beginning
    0.08
    Activations Density 0.081%

    No Known Activations