© 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. 88541
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and its variations in different contexts

    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
    LD
    -0.06
    not
    -0.06
     behalf
    -0.06
    cd
    -0.06
     Ke
    -0.06
     distur
    -0.06
     اÙĦعظ
    -0.05
    eded
    -0.05
     tam
    -0.05
     ke
    -0.05
    POSITIVE LOGITS
    herits
    0.08
    affen
    0.08
    azon
    0.07
    pollo
    0.07
    abaj
    0.07
    iyat
    0.07
     UObject
    0.07
    rett
    0.07
    415
    0.07
    omain
    0.07
    Activations Density 0.050%

    No Known Activations