© 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. 15-LLAMASCOPE-RES-131K
    11. 88465
    Prev
    Next
    INDEX
    Explanations

    articles and determiners that indicate the presence of nouns or noun phrases

    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
    æīĺ
    -0.07
    anks
    -0.06
    оÑĩной
    -0.06
    ovel
    -0.06
    âĨIJ
    -0.06
    anc
    -0.06
    ologue
    -0.06
    ecal
    -0.05
     disg
    -0.05
     renderItem
    -0.05
    POSITIVE LOGITS
    edn
    0.07
    ëĨ
    0.07
    taire
    0.06
    ÙĦاÙĨ
    0.06
    uforia
    0.06
    umbing
    0.06
    ç²¾åĵģ
    0.06
    è¡Ĩ
    0.06
    ption
    0.06
     Franco
    0.06
    Activations Density 0.036%

    No Known Activations