© 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. 80250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and emphasizes its frequency in various 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
     pud
    -0.06
    :
    -0.06
    ysis
    -0.06
     gar
    -0.06
     version
    -0.06
    aan
    -0.05
     fusion
    -0.05
     entirety
    -0.05
     pij
    -0.05
     gob
    -0.05
    POSITIVE LOGITS
     us
    0.07
    ourn
    0.07
     me
    0.07
    Ø®Ùħ
    0.07
    echa
    0.06
    é³
    0.06
    804
    0.06
    ÑģÑĤеÑĢ
    0.06
    logan
    0.06
    ignum
    0.06
    Activations Density 0.014%

    No Known Activations