© 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. 14775
    Prev
    Next
    INDEX
    Explanations

    references to academic research and scientific details

    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
    PRINTF
    -0.06
     foss
    -0.06
    Tau
    -0.06
    ixo
    -0.06
    å±ħæ°ij
    -0.06
    одÑĥ
    -0.06
     pitches
    -0.06
     leisure
    -0.06
     Animalia
    -0.06
    FragmentManager
    -0.06
    POSITIVE LOGITS
     plant
    0.10
     Plant
    0.09
    Plant
    0.09
    yled
    0.09
     shoot
    0.09
     planta
    0.08
     Dwarf
    0.08
     plants
    0.08
     Plants
    0.08
     dwar
    0.08
    Activations Density 0.121%

    No Known Activations