© 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. 15-LLAMASCOPE-RES-131K
    11. 27388
    Prev
    Next
    INDEX
    Explanations

    references to television and related media content

    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
    oko
    -0.09
    heim
    -0.08
    elp
    -0.07
    ëģĶ
    -0.07
    ób
    -0.07
    ëĬĶ
    -0.07
    éĩį大
    -0.07
    élé
    -0.07
    leigh
    -0.07
    íĴĪ
    -0.07
    POSITIVE LOGITS
    ized
    0.08
    625
    0.07
    ously
    0.07
    ãģĤãĤĭ
    0.07
    naire
    0.07
    ISED
    0.07
    arası
    0.07
    cete
    0.07
    âķĿ
    0.07
    taire
    0.07
    Activations Density 0.008%

    No Known Activations