© 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. 117862
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate varying opinions or criticisms

    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
    acea
    -0.07
    xad
    -0.07
    emean
    -0.07
    ãģ¼
    -0.06
    veis
    -0.06
    pras
    -0.06
    ivor
    -0.06
     McGr
    -0.06
     alcoholic
    -0.06
    ptime
    -0.06
    POSITIVE LOGITS
     this
    0.15
     these
    0.14
    è¿Ļç§į
    0.13
    this
    0.12
    è¿Ļ个
    0.12
    è¿Ļæł·çļĦ
    0.11
    these
    0.11
     nÃły
    0.11
     questa
    0.10
     These
    0.10
    Activations Density 0.074%

    No Known Activations