© 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. 14782
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent to take 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
    ÑĩаÑģно
    -0.07
    ÑĢÑĸÑĪ
    -0.07
    eam
    -0.07
    ãĤ¥
    -0.07
    _NEAREST
    -0.06
    Ñıв
    -0.06
    оÑĤÑĮ
    -0.06
    ieber
    -0.06
    ож
    -0.06
    velop
    -0.06
    POSITIVE LOGITS
     to
    0.09
    inkle
    0.07
    aida
    0.06
    antly
    0.06
    (es
    0.06
    fully
    0.06
    еÑĢо
    0.06
    ÅĻiv
    0.06
    iyel
    0.06
    entially
    0.06
    Activations Density 0.007%

    No Known Activations