© 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. 5-LLAMASCOPE-RES-131K
    11. 125610
    Prev
    Next
    INDEX
    Explanations

    references to significant or notable events and their timing

    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
    urs
    -0.07
    ÑĮми
    -0.07
    inke
    -0.06
    дÑĢом
    -0.06
    ipple
    -0.06
    ETS
    -0.06
     Äijấu
    -0.06
    ặt
    -0.06
    edom
    -0.06
    اÙĩÙħ
    -0.06
    POSITIVE LOGITS
    æľī人
    0.06
    rame
    0.06
    arde
    0.06
    548
    0.06
    jedn
    0.06
    aea
    0.06
    airy
    0.06
    ocos
    0.06
    åĪ¶
    0.06
    ington
    0.06
    Activations Density 0.006%

    No Known Activations