© 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. 14499
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to welding processes and mining methods

    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
    rana
    -0.08
     اÙģت
    -0.07
     обÑĢаз
    -0.07
     sobie
    -0.07
    олж
    -0.06
    eeper
    -0.06
    ought
    -0.06
    marca
    -0.06
    .memo
    -0.06
    yne
    -0.06
    POSITIVE LOGITS
     technique
    0.14
     method
    0.12
     Technique
    0.11
     involving
    0.09
     performed
    0.09
     techniques
    0.09
    method
    0.09
     practiced
    0.08
    ä¸Ģç§į
    0.08
     process
    0.08
    Activations Density 0.084%

    No Known Activations