© 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. 62380
    Prev
    Next
    INDEX
    Explanations

    references to food and dining establishments

    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
    ÌĨ
    -0.06
     Rise
    -0.06
    incinn
    -0.06
    .LayoutStyle
    -0.06
    teri
    -0.05
     battlefield
    -0.05
    eres
    -0.05
     MainAxisAlignment
    -0.05
     Dexter
    -0.05
    ̧
    -0.05
    POSITIVE LOGITS
     franch
    0.08
    Invariant
    0.07
    atur
    0.07
    aturas
    0.07
     patented
    0.07
    uru
    0.07
    .GetObject
    0.07
    bras
    0.06
     Gott
    0.06
    iros
    0.06
    Activations Density 0.008%

    No Known Activations