© 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. 38941
    Prev
    Next
    INDEX
    Explanations

    elements related to web design or layout specifications

    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
    -|
    -0.06
    ace
    -0.06
    655
    -0.06
    hti
    -0.06
    lops
    -0.06
     impe
    -0.06
    eless
    -0.06
    a
    -0.06
     trailing
    -0.06
    åijĢ
    -0.05
    POSITIVE LOGITS
    CAA
    0.07
    omor
    0.07
    ifice
    0.07
    boru
    0.07
    AllWindows
    0.07
    /drivers
    0.07
    san
    0.07
    istance
    0.07
    icals
    0.07
    gress
    0.06
    Activations Density 0.049%

    No Known Activations