© 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. 72808
    Prev
    Next
    INDEX
    Explanations

    phrases associated with immersive experiences and entertainment initiatives

    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
     intr
    -0.08
     intra
    -0.06
    åĦĢ
    -0.06
    ноÑĩ
    -0.06
     suicidal
    -0.06
    åĶĩ
    -0.06
     Rescue
    -0.06
     backup
    -0.06
    è°ĥ
    -0.06
    Zoom
    -0.06
    POSITIVE LOGITS
    uars
    0.08
    าหล
    0.07
    ugar
    0.07
    apiro
    0.07
     Experience
    0.07
    :convert
    0.07
    ngth
    0.07
    VOID
    0.07
     immersive
    0.07
     experience
    0.06
    Activations Density 0.011%

    No Known Activations