© 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. 15-LLAMASCOPE-RES-131K
    11. 87687
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate intention or desire

    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
    uttle
    -0.07
    aN
    -0.07
    yst
    -0.06
    rien
    -0.06
    rio
    -0.06
    ads
    -0.06
    EDI
    -0.06
    ãĥ¼ãĥķ
    -0.06
    温
    -0.06
    reason
    -0.06
    POSITIVE LOGITS
     to
    0.14
    åĪ°çļĦ
    0.13
    åĪ°
    0.09
    lessly
    0.09
    äºİ
    0.09
    sto
    0.07
    entially
    0.07
    encer
    0.07
    fully
    0.07
     Ø¥ÙĦÙī
    0.07
    Activations Density 0.051%

    No Known Activations