© 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. 88915
    Prev
    Next
    INDEX
    Explanations

    references to web development and programming concepts

    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
    åı¯èĥ½æĢ§
    -0.07
     eens
    -0.07
    جÛĮ
    -0.07
     æĴ
    -0.07
    ôt
    -0.07
    eres
    -0.06
    γγ
    -0.06
    asant
    -0.06
    cis
    -0.06
     âĩ
    -0.06
    POSITIVE LOGITS
     appears
    0.08
     appear
    0.07
     seems
    0.06
    pite
    0.06
     remained
    0.06
     gets
    0.06
    ordinate
    0.06
    nam
    0.06
    лаÑĪ
    0.06
    uddenly
    0.06
    Activations Density 0.026%

    No Known Activations