© 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. 15-LLAMASCOPE-RES-131K
    11. 86566
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to analog technology or characteristics

    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
     latter
    -0.07
    aley
    -0.07
     kenn
    -0.06
    ÄĽÅ¾
    -0.06
    elyn
    -0.06
    igan
    -0.06
    blade
    -0.06
    ãģ¤ãģ¶
    -0.06
    ukes
    -0.06
    igung
    -0.06
    POSITIVE LOGITS
    ues
    0.15
    ued
    0.10
    ical
    0.10
    ically
    0.10
    UES
    0.09
    UE
    0.09
    ue
    0.08
    hee
    0.08
    ies
    0.08
    uet
    0.08
    Activations Density 0.041%

    No Known Activations