© 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. 40415
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related syntax elements

    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
    Ń
    -0.07
    ropri
    -0.07
    eded
    -0.06
    997
    -0.06
    tility
    -0.06
    esis
    -0.06
    ê´Ģ
    -0.06
     Ellison
    -0.06
    avad
    -0.06
     Jord
    -0.06
    POSITIVE LOGITS
    alers
    0.07
    3
    0.07
    ippi
    0.06
    Desk
    0.06
     Shrine
    0.06
     shrine
    0.06
    inkle
    0.06
    4
    0.06
    gesch
    0.06
    hle
    0.06
    Activations Density 0.002%

    No Known Activations