© 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. 59501
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the creation of content or pages

    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
    agate
    -0.08
     æ¨
    -0.06
    ½
    -0.06
     Gros
    -0.06
    abus
    -0.06
    aleb
    -0.05
     noisy
    -0.05
    abwe
    -0.05
     Localization
    -0.05
    ter
    -0.05
    POSITIVE LOGITS
    uru
    0.07
    inston
    0.07
     Lynch
    0.07
     Dot
    0.06
    alternate
    0.06
    emy
    0.06
     çŁ
    0.06
    _altern
    0.06
     >č↵
    0.06
    irk
    0.06
    Activations Density 0.000%

    No Known Activations