© 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. 57773
    Prev
    Next
    INDEX
    Explanations

    citations and publication information in research documents

    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
    se
    -0.06
     squat
    -0.06
    onen
    -0.06
    itis
    -0.06
    implify
    -0.06
    eller
    -0.05
    il
    -0.05
     compar
    -0.05
     square
    -0.05
    ç¦ı
    -0.05
    POSITIVE LOGITS
     acept
    0.08
    oola
    0.08
    .Accept
    0.08
    chartInstance
    0.08
     ACCEPT
    0.08
    enko
    0.08
    elerik
    0.07
    aÅĻ
    0.07
    SupportedContent
    0.07
    aklı
    0.07
    Activations Density 0.004%

    No Known Activations