© 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 EvalsExportsAPI 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. 56178
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to mathematics and programming

    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
     scaleY
    -0.08
    èĪĮ
    -0.07
    -ng
    -0.07
    à¥įयम
    -0.07
     MetroFramework
    -0.06
     åŀ
    -0.06
    Dual
    -0.06
     sür
    -0.06
    HING
    -0.06
    .sap
    -0.06
    POSITIVE LOGITS
     third
    0.10
    3
    0.10
     Third
    0.08
     THIRD
    0.08
     tercer
    0.07
    -third
    0.07
    yna
    0.07
    third
    0.07
    uly
    0.07
    Third
    0.07
    Activations Density 0.133%

    No Known Activations