© 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. 62483
    Prev
    Next
    INDEX
    Explanations

    verbs related to approval, improvement, and organizational actions

    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
     u
    -0.07
     ‘
    -0.06
    312
    -0.06
     Kul
    -0.06
     onto
    -0.06
    668
    -0.06
    omba
    -0.06
    168
    -0.05
    428
    -0.05
    533
    -0.05
    POSITIVE LOGITS
    kich
    0.08
     jadx
    0.07
    ç¿Ķ
    0.07
    .liferay
    0.07
    ibility
    0.07
     tavs
    0.07
    rouch
    0.07
    _CHIP
    0.07
     ydk
    0.07
    ãĥ³ãĤ°ãĥ«
    0.07
    Activations Density 0.055%

    No Known Activations