© 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. 91534
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations of experiences or items, particularly involving feelings towards art and history

    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
    otte
    -0.08
    inka
    -0.06
    jab
    -0.06
    éĺ´
    -0.06
     PureComponent
    -0.06
    ä¸ĬäºĨ
    -0.06
    /apis
    -0.05
    alan
    -0.05
    ủng
    -0.05
     now
    -0.05
    POSITIVE LOGITS
    æŁIJ
    0.15
     someone
    0.12
     somebody
    0.12
    someone
    0.12
     sebuah
    0.10
     alguien
    0.10
    ä¸Ģ个
    0.10
    ä¸ĢåĢĭ
    0.09
     æŁ
    0.09
     ìĸ´ëĸ¤
    0.09
    Activations Density 0.120%

    No Known Activations