© 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. 86357
    Prev
    Next
    INDEX
    Explanations

    phrases indicating benefits or advantages derived from various sources or experiences

    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
    onde
    -0.08
    èo
    -0.08
    orris
    -0.08
     riêng
    -0.08
    AWN
    -0.07
     chấp
    -0.07
    à¸Ļà¸Ħ
    -0.07
    ept
    -0.07
    ivation
    -0.07
    reas
    -0.07
    POSITIVE LOGITS
     being
    0.08
     having
    0.07
     decreased
    0.07
     increased
    0.07
    lessly
    0.07
    iez
    0.06
    ably
    0.06
    467
    0.06
     proximity
    0.06
    ximity
    0.06
    Activations Density 0.011%

    No Known Activations