© 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. 87180
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of impatience or impulse control

    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
    abis
    -0.08
    ãĢħ
    -0.07
    annis
    -0.07
    lad
    -0.07
    æĭ©
    -0.07
    sume
    -0.07
    radi
    -0.07
    icker
    -0.07
    ervals
    -0.06
    hs
    -0.06
    POSITIVE LOGITS
    sterol
    0.08
    ment
    0.08
    ément
    0.07
    antly
    0.07
    æĢ§çļĦ
    0.07
    ments
    0.07
    uous
    0.07
    urge
    0.06
     quot
    0.06
    ans
    0.06
    Activations Density 0.018%

    No Known Activations