© 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. 18439
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" indicating purpose or intent

    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
    /kernel
    -0.06
    бина
    -0.06
    istes
    -0.06
     tends
    -0.06
    ãĥ¼ãĤ¯
    -0.06
     ensure
    -0.06
    jure
    -0.06
    ories
    -0.06
     Hath
    -0.06
     hast
    -0.05
    POSITIVE LOGITS
     hear
    0.09
     hearing
    0.08
    åIJ¬åĪ°
    0.07
    animate
    0.07
     hears
    0.07
    ÅĦst
    0.07
    tae
    0.07
    latable
    0.07
     receive
    0.06
     Rece
    0.06
    Activations Density 0.018%

    No Known Activations