© 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. 107642
    Prev
    Next
    INDEX
    Explanations

    transformative phrases that describe changes or enhancements in various contexts

    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
    imits
    -0.06
    ¯
    -0.06
    hn
    -0.06
    orum
    -0.06
    stood
    -0.06
    ding
    -0.06
    chants
    -0.06
    lem
    -0.06
    rone
    -0.06
    inkle
    -0.06
    POSITIVE LOGITS
    æł·åŃIJ
    0.09
     launching
    0.07
    sert
    0.07
    bec
    0.07
    arser
    0.06
    cept
    0.06
     detriment
    0.06
    ãģ¸ãģ¨
    0.06
     overnight
    0.06
     something
    0.06
    Activations Density 0.028%

    No Known Activations