© 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. 53904
    Prev
    Next
    INDEX
    Explanations

    similes and comparisons related to sensations and experiences

    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
    078
    -0.08
    inka
    -0.07
    089
    -0.07
    oley
    -0.06
    088
    -0.06
    åģ
    -0.06
    XXX
    -0.06
    lia
    -0.06
    dden
    -0.06
    achuset
    -0.06
    POSITIVE LOGITS
    æ´»
    0.07
    ãģ¾ãĤĭ
    0.07
    erval
    0.07
    lamaz
    0.07
    iche
    0.07
     Poss
    0.07
     Bias
    0.07
    AGMA
    0.07
    гÑĥ
    0.07
     unto
    0.06
    Activations Density 0.023%

    No Known Activations