© 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. 93175
    Prev
    Next
    INDEX
    Explanations

    elements related to music and educational activities involving answers and coloring

    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
    ichel
    -0.07
    zion
    -0.06
    cesso
    -0.06
    amine
    -0.06
    otte
    -0.06
    екÑģи
    -0.05
    lane
    -0.05
    AFF
    -0.05
    loh
    -0.05
    ndl
    -0.05
    POSITIVE LOGITS
     correct
    0.07
    Äįit
    0.07
    æŃ£ç¡®
    0.07
     appropriate
    0.07
     matching
    0.06
    ¼åIJĪ
    0.06
    彦
    0.06
    åĮ¹
    0.06
     correctly
    0.06
     Mystery
    0.06
    Activations Density 0.007%

    No Known Activations