© 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. 105772
    Prev
    Next
    INDEX
    Explanations

    structured plans, agreements, and frameworks related to projects or policies

    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
    isko
    -0.07
     hern
    -0.07
    Erot
    -0.06
    SWG
    -0.06
    ienie
    -0.06
    INGTON
    -0.06
    ERA
    -0.06
    åł
    -0.06
     STD
    -0.06
    -Methods
    -0.06
    POSITIVE LOGITS
     plan
    0.08
    è§Ħå®ļ
    0.08
    åħģ
    0.07
     пÑĢедÑĥÑģ
    0.07
    mlin
    0.07
    repos
    0.07
    wor
    0.07
     agreement
    0.07
     agreed
    0.07
    plan
    0.07
    Activations Density 0.041%

    No Known Activations