© 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. 15-LLAMASCOPE-RES-131K
    11. 86162
    Prev
    Next
    INDEX
    Explanations

    phrases related to justification and validation of perspectives or opinions

    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
    eil
    -0.08
    oto
    -0.07
    ãģıãĤī
    -0.07
    çŁ¢
    -0.07
    oris
    -0.06
    jas
    -0.06
    oggler
    -0.06
    eus
    -0.06
    -gnu
    -0.06
    磨
    -0.06
    POSITIVE LOGITS
     equally
    0.18
     equal
    0.10
     igual
    0.09
     EQUAL
    0.08
     valid
    0.08
    _equal
    0.08
    equal
    0.07
     równ
    0.07
    -valid
    0.07
     Equ
    0.07
    Activations Density 0.091%

    No Known Activations