© 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. 92953
    Prev
    Next
    INDEX
    Explanations

    the "ly" suffix in words related to plotting or data visualization

    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
    rita
    -0.06
    ApiClient
    -0.06
    ai
    -0.06
    thinkable
    -0.06
    ried
    -0.06
    ï¸ı
    -0.06
    енка
    -0.06
    ario
    -0.05
    د
    -0.05
    ilia
    -0.05
    POSITIVE LOGITS
    'gc
    0.08
    _marshall
    0.08
    .scalablytyped
    0.07
    URES
    0.07
    asters
    0.07
    isclosed
    0.07
    .setDefault
    0.06
    icontrol
    0.06
     íĨµíķ©
    0.06
    ering
    0.06
    Activations Density 0.000%

    No Known Activations