© 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. 117697
    Prev
    Next
    INDEX
    Explanations

    HTML link attributes in a web document

    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
    ante
    -0.06
     rig
    -0.06
    ari
    -0.06
     gal
    -0.06
    -Ðij
    -0.06
     radi
    -0.06
    iations
    -0.06
    104
    -0.06
    amura
    -0.06
    arsi
    -0.05
    POSITIVE LOGITS
    agher
    0.08
    istring
    0.07
    lesia
    0.06
    надлеж
    0.06
    utches
    0.06
    lux
    0.06
    sik
    0.06
    ButtonTitles
    0.06
    ädchen
    0.06
     putas
    0.06
    Activations Density 0.002%

    No Known Activations