© 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 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. 126600
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases that indicate relationships or connections

    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
    aisy
    -0.06
     pur
    -0.06
     equally
    -0.06
     high
    -0.06
    ren
    -0.06
    ela
    -0.06
    orthy
    -0.06
     cap
    -0.06
     Variant
    -0.06
     ground
    -0.06
    POSITIVE LOGITS
    abbo
    0.08
    omit
    0.08
    ↵↵
    0.08
    lest
    0.07
    pez
    0.07
    $LANG
    0.07
    HeaderCode
    0.07
    ãĤ´ãĥª
    0.07
    ropolis
    0.07
    RITE
    0.07
    Activations Density 0.035%

    No Known Activations