© 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. 18440
    Prev
    Next
    INDEX
    Explanations

    mentions of technical skills and proficiency in software applications

    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
    ogs
    -0.06
    帽
    -0.06
    imar
    -0.06
    ноз
    -0.06
     Definitions
    -0.06
    oves
    -0.05
     Sporting
    -0.05
    ulu
    -0.05
    erson
    -0.05
    eros
    -0.05
    POSITIVE LOGITS
    íݸ
    0.07
     Odyssey
    0.07
    Microsoft
    0.06
     Microsoft
    0.06
    Ctrls
    0.06
    comfort
    0.06
    _BS
    0.06
    yntax
    0.06
    illez
    0.06
     Manip
    0.06
    Activations Density 0.015%

    No Known Activations