© 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. 95651
    Prev
    Next
    INDEX
    Explanations

    positive descriptors related to experiences and challenges

    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
    currently
    -0.07
    bios
    -0.07
    still
    -0.07
     potential
    -0.07
     still
    -0.07
    è¿ĺæľī
    -0.07
     Jog
    -0.07
     possibilities
    -0.06
    omial
    -0.06
     currently
    -0.06
    POSITIVE LOGITS
     since
    0.10
     lately
    0.10
    _since
    0.08
    since
    0.08
    Since
    0.07
     consistent
    0.07
     Since
    0.07
    tah
    0.07
    ìĽĶë¶ĢíĦ°
    0.06
    addy
    0.06
    Activations Density 0.016%

    No Known Activations