© 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. 3504
    Prev
    Next
    INDEX
    Explanations

    mentions of Austria and related terms

    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
    rine
    -0.07
    zi
    -0.07
    igned
    -0.06
    zilla
    -0.06
    orthand
    -0.06
    ãĥĥãĤ°
    -0.06
    stone
    -0.06
    isode
    -0.06
    stead
    -0.06
    pest
    -0.06
    POSITIVE LOGITS
    imler
    0.08
     Alps
    0.07
    каÑģ
    0.07
    andom
    0.06
    652
    0.06
    emma
    0.06
    ought
    0.06
    754
    0.06
    /proto
    0.06
    /javascript
    0.06
    Activations Density 0.006%

    No Known Activations