© 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. 5305
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to project management, specifically in build files

    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
    rotation
    -0.07
     Fay
    -0.06
    501
    -0.06
    ×ķ×
    -0.06
    sur
    -0.06
    interval
    -0.06
    Leod
    -0.06
    rrha
    -0.06
    ched
    -0.06
    edd
    -0.06
    POSITIVE LOGITS
    mium
    0.07
    ivec
    0.07
    ADF
    0.07
    à¸ģรรม
    0.07
    imeline
    0.06
    odesk
    0.06
    ÃŃst
    0.06
    oden
    0.06
     èĢ
    0.06
    teri
    0.06
    Activations Density 0.000%

    No Known Activations