© 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. 119237
    Prev
    Next
    INDEX
    Explanations

    phrases related to chickpeas and their culinary uses

    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
    .sponge
    -0.07
    èĺ
    -0.07
    seau
    -0.07
    ród
    -0.06
    -addon
    -0.06
    æı®
    -0.06
    pent
    -0.06
    grass
    -0.06
     Bread
    -0.06
    Sugar
    -0.06
    POSITIVE LOGITS
    beans
    0.08
     bean
    0.08
    è±Ĩ
    0.07
     beans
    0.07
    ocks
    0.07
    anko
    0.06
    ekler
    0.06
    Extras
    0.06
    bean
    0.06
     Bean
    0.06
    Activations Density 0.016%

    No Known Activations