© 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. 40364
    Prev
    Next
    INDEX
    Explanations

    phrases involving the verbs "to" followed by an action

    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
    \Unit
    -0.08
    igham
    -0.08
     VÅ¡ech
    -0.08
    .ease
    -0.07
     bekl
    -0.07
    lse
    -0.07
    vailability
    -0.07
    ALS
    -0.07
    ارÛĮ
    -0.07
    ê°ij
    -0.07
    POSITIVE LOGITS
     recently
    0.07
     originally
    0.07
    RT
    0.06
    éĤ
    0.06
     almost
    0.06
    n
    0.06
    t
    0.06
     Inherits
    0.06
     Tweet
    0.05
     twice
    0.05
    Activations Density 0.023%

    No Known Activations