© 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. 120150
    Prev
    Next
    INDEX
    Explanations

    actions related to user interaction with software or application interfaces

    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
    ena
    -0.07
    -based
    -0.06
    rit
    -0.06
     st
    -0.06
     native
    -0.06
     based
    -0.06
    ana
    -0.06
    ilo
    -0.06
    icks
    -0.06
    Verse
    -0.06
    POSITIVE LOGITS
    chwitz
    0.07
    ief
    0.07
    .utf
    0.07
    hled
    0.07
    LIKELY
    0.07
    erce
    0.07
    straints
    0.06
    onne
    0.06
    ãĥĮ
    0.06
    AME
    0.06
    Activations Density 0.006%

    No Known Activations