© 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. 86554
    Prev
    Next
    INDEX
    Explanations

    personal sentiments and expressions of emotion

    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
    -0.07
    584
    -0.07
    ÑĥлÑı
    -0.06
    336
    -0.06
    .Framework
    -0.06
    jvu
    -0.06
    mada
    -0.06
    pek
    -0.06
    337
    -0.06
     (
    -0.06
    POSITIVE LOGITS
    orer
    0.07
    lesh
    0.07
    oes
    0.07
    çĬ
    0.07
    .generic
    0.07
    iston
    0.06
     Fischer
    0.06
    oves
    0.06
    .react
    0.06
    جÙĩ
    0.06
    Activations Density 0.026%

    No Known Activations