© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129443
    Prev
    Next
    INDEX
    Explanations

    terms related to complexity and advancement in various contexts

    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
    AZY
    -0.08
    hot
    -0.07
    inous
    -0.07
    tings
    -0.06
    azon
    -0.06
    uzu
    -0.06
    nis
    -0.06
    atha
    -0.06
    oldur
    -0.06
    indow
    -0.06
    POSITIVE LOGITS
    -looking
    0.10
    ed
    0.09
    seau
    0.08
     enough
    0.08
    pj
    0.07
    edn
    0.07
    -minded
    0.07
    ayette
    0.07
    elho
    0.07
    ienda
    0.07
    Activations Density 0.003%

    No Known Activations