© 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. 108433
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of appreciation and valuing

    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
    arp
    -0.07
    obi
    -0.07
    arna
    -0.07
    aring
    -0.07
    izzy
    -0.07
     пов
    -0.06
    unami
    -0.06
    _press
    -0.06
    ù
    -0.06
    .emf
    -0.06
    POSITIVE LOGITS
    ably
    0.12
    ately
    0.10
    iable
    0.07
    ible
    0.07
    full
    0.07
    SSION
    0.07
    ively
    0.07
    erence
    0.07
    fully
    0.07
    iative
    0.06
    Activations Density 0.009%

    No Known Activations