© 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. 104804
    Prev
    Next
    INDEX
    Explanations

    terms related to interdisciplinary studies and collaboration

    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
    ucz
    -0.08
    eo
    -0.08
     hete
    -0.07
    okit
    -0.07
    miss
    -0.07
    raz
    -0.07
    nz
    -0.07
    алеж
    -0.07
    ÄįenÃŃ
    -0.07
    ras
    -0.07
    POSITIVE LOGITS
     approach
    0.10
     Approach
    0.08
    appro
    0.08
     approaches
    0.08
     nature
    0.07
     teams
    0.07
    nature
    0.07
    ism
    0.07
     Appro
    0.07
    nes
    0.06
    Activations Density 0.005%

    No Known Activations