© 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. 54101
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and the enjoyment of activities

    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
    ragen
    -0.08
    AccessException
    -0.07
    upro
    -0.07
    ega
    -0.07
    xca
    -0.07
    orman
    -0.07
    人人
    -0.07
    ÑĮко
    -0.07
     Compact
    -0.06
    egal
    -0.06
    POSITIVE LOGITS
    559
    0.07
     HAL
    0.06
    amine
    0.06
    peri
    0.06
    worthy
    0.06
    gio
    0.06
    pak
    0.06
     Nx
    0.06
     fois
    0.05
    اÛĮØ´
    0.05
    Activations Density 0.007%

    No Known Activations