© 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. 80104
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and qualities that convey emotions or attributes

    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
    ighet
    -0.08
    AndView
    -0.07
    aka
    -0.07
     &
    -0.06
    ÅĦst
    -0.06
    inue
    -0.06
    igh
    -0.06
    incr
    -0.06
    inth
    -0.06
    _and
    -0.06
    POSITIVE LOGITS
     alike
    0.10
    راÙĨÙĩ
    0.07
    ly
    0.07
    æģ
    0.07
    afil
    0.07
     Hao
    0.07
    licant
    0.06
    oster
    0.06
    ness
    0.06
     manner
    0.06
    Activations Density 0.049%

    No Known Activations