© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107142
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate direction or movement

    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
    ilor
    -0.07
     Bret
    -0.07
     >č↵
    -0.07
    .party
    -0.06
    .lu
    -0.06
    онÑĮ
    -0.06
    ÙĨÚ¯ÛĮ
    -0.06
    /cs
    -0.06
    оÑģÑĤаÑĤ
    -0.06
    ouve
    -0.06
    POSITIVE LOGITS
     back
    0.07
    oute
    0.06
    ipse
    0.06
     down
    0.06
    earning
    0.06
    itler
    0.06
    ży
    0.06
    tet
    0.06
     Zhao
    0.06
    Mos
    0.06
    Activations Density 0.006%

    No Known Activations