© 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. 88630
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and aspiration

    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
     albeit
    -0.06
    012
    -0.06
    pv
    -0.06
    atts
    -0.06
    contre
    -0.06
     Extra
    -0.06
    erap
    -0.06
    egan
    -0.06
    frauen
    -0.06
    ilst
    -0.05
    POSITIVE LOGITS
     succeed
    0.07
    оÑģÑĮ
    0.07
     believe
    0.07
     succeeds
    0.07
     noble
    0.07
     اÙĦعÙĤ
    0.06
    yal
    0.06
    ucceed
    0.06
    oble
    0.06
    ãĥĨãĥ«
    0.06
    Activations Density 0.022%

    No Known Activations