© 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 EvalsExportsinterp-engineNEWAPI 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. 95228
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to design and functionality

    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
    åĿĽ
    -0.07
     подв
    -0.07
    _inches
    -0.07
    issen
    -0.07
    871
    -0.06
    trainer
    -0.06
    utan
    -0.06
    座
    -0.06
    ya
    -0.06
    oplevel
    -0.06
    POSITIVE LOGITS
     separate
    0.07
    ably
    0.06
    ãĥ³ãĤ¿
    0.06
    ارش
    0.06
    itom
    0.06
     Noel
    0.06
    othy
    0.06
     corresponding
    0.06
    ý
    0.06
     imkân
    0.06
    Activations Density 0.020%

    No Known Activations