© 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. 58716
    Prev
    Next
    INDEX
    Explanations

    indicators of article formatting and structure

    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
    é¡ŀ
    -0.06
     accompany
    -0.06
    ize
    -0.06
    ke
    -0.06
    ermann
    -0.06
    horn
    -0.06
    oni
    -0.06
    ht
    -0.06
    onna
    -0.05
    ована
    -0.05
    POSITIVE LOGITS
    ì¦Ŀ
    0.08
    á»ĭp
    0.07
    ë²Į
    0.07
    é¨
    0.07
    undle
    0.07
    TEE
    0.07
    (UnityEngine
    0.06
    यर
    0.06
    patches
    0.06
    ysize
    0.06
    Activations Density 0.001%

    No Known Activations