© 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 EvalsExportsAPI 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. 89255
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement, happiness, and positive emotions

    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
    cis
    -0.07
     Levine
    -0.06
    laws
    -0.06
    anz
    -0.06
    è¼Ŀ
    -0.06
    sti
    -0.06
    Bes
    -0.05
     SENT
    -0.05
    legt
    -0.05
    Segment
    -0.05
    POSITIVE LOGITS
    ionic
    0.07
    edio
    0.07
    elsen
    0.07
    .dc
    0.07
    hausen
    0.07
     disappe
    0.07
    Gro
    0.07
    \Migration
    0.06
    हन
    0.06
     pac
    0.06
    Activations Density 0.017%

    No Known Activations