© 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. 80423
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "interface"

    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
    li
    -0.09
    nen
    -0.08
    lia
    -0.07
    mega
    -0.07
    thy
    -0.07
    acher
    -0.07
    amber
    -0.07
    na
    -0.07
    н
    -0.07
    reich
    -0.07
    POSITIVE LOGITS
    pread
    0.07
    .OnClickListener
    0.07
    ettings
    0.07
    ños
    0.07
    .Interface
    0.07
    bell
    0.06
    /interface
    0.06
    copy
    0.06
    ually
    0.06
    ntax
    0.06
    Activations Density 0.018%

    No Known Activations