© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5990
    Prev
    Next
    INDEX
    Explanations

    relationships involving Earth and space in a scientific context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãĥĭãĥĥãĤ¯
    -0.09
    eyle
    -0.07
    rir
    -0.07
    storybook
    -0.07
     Winds
    -0.07
    ideographic
    -0.07
    ÏĪη
    -0.07
    ervo
    -0.07
    weathermap
    -0.07
    æݪ
    -0.07
    POSITIVE LOGITS
     Earth
    0.13
     earth
    0.13
    Earth
    0.11
     humans
    0.09
    earth
    0.08
     human
    0.08
    åľ°çIJĥ
    0.08
     earthly
    0.08
     humanity
    0.07
    hum
    0.07
    Activations Density 0.015%

    No Known Activations