© 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. 104817
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual quality and media experience

    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
    決
    -0.06
    GPS
    -0.06
     Grove
    -0.06
     bilingual
    -0.06
    nev
    -0.06
    ometr
    -0.06
     chic
    -0.06
    æī
    -0.06
     temper
    -0.06
    Pager
    -0.05
    POSITIVE LOGITS
     viewing
    0.09
     motion
    0.08
     experience
    0.08
     Experience
    0.07
    experience
    0.07
    ipeg
    0.07
    olah
    0.07
    oleÄį
    0.07
     Motion
    0.07
    owitz
    0.07
    Activations Density 0.009%

    No Known Activations