© 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. 73342
    Prev
    Next
    INDEX
    Explanations

    references to animal-related interactions and challenges in a natural environment

    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
     Hatch
    -0.06
    zas
    -0.06
    palette
    -0.06
     Appalach
    -0.06
    lems
    -0.06
    umo
    -0.06
     onward
    -0.05
    elerine
    -0.05
    .oc
    -0.05
    otime
    -0.05
    POSITIVE LOGITS
     introduced
    0.09
    à¸Ĩ
    0.07
    Introduced
    0.07
     Introduced
    0.07
    ãĥ³ãĥģ
    0.07
     Bernardino
    0.07
    _Manager
    0.07
    åı°
    0.07
    /fontawesome
    0.07
    /drivers
    0.07
    Activations Density 0.005%

    No Known Activations