© 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. 104846
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements and considerations in various processes

    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
    lj
    -0.07
    Constructed
    -0.07
    ield
    -0.07
    ειο
    -0.07
    ior
    -0.07
    kos
    -0.07
     JFK
    -0.07
    ATAR
    -0.06
    /UIKit
    -0.06
    è£ľ
    -0.06
    POSITIVE LOGITS
    Sharp
    0.07
    omat
    0.07
     ê³łëł¤
    0.07
    hong
    0.06
     consideration
    0.06
    Points
    0.06
     accomplish
    0.06
     Sharp
    0.06
    ¦Ĥ
    0.06
    cura
    0.06
    Activations Density 0.024%

    No Known Activations