© 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. 76547
    Prev
    Next
    INDEX
    Explanations

    the word "however"

    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
    inz
    -0.08
     же
    -0.07
    peats
    -0.07
    dera
    -0.07
    kos
    -0.07
    INCLUDED
    -0.07
    INDER
    -0.07
    _cmp
    -0.07
    ford
    -0.07
    /animate
    -0.06
    POSITIVE LOGITS
    -Sah
    0.06
    ioc
    0.06
     Gregg
    0.06
    eded
    0.06
    cassert
    0.06
    iot
    0.06
    apolis
    0.05
    lotte
    0.05
     pag
    0.05
    InstanceState
    0.05
    Activations Density 0.011%

    No Known Activations