© 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. 105001
    Prev
    Next
    INDEX
    Explanations

    instances of emotional language or expressions of sentiment

    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
     people
    -0.07
    /people
    -0.07
     publicity
    -0.07
    æĬĬ
    -0.07
    uy
    -0.06
     different
    -0.06
     diferentes
    -0.06
     ê³ĦìĨį
    -0.06
     uses
    -0.06
    &gt
    -0.06
    POSITIVE LOGITS
    ãģ«ãģ¦
    0.08
     aforementioned
    0.07
    .Compose
    0.07
    ipsis
    0.07
    èµĸ
    0.07
    arth
    0.06
    ÙģÙĩÙĪÙħ
    0.06
    upon
    0.06
    soever
    0.06
    emploi
    0.06
    Activations Density 3.500%

    No Known Activations