© 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. 26907
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing quantification or numerical comparisons

    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
    Ïģαβ
    -0.08
     Hüs
    -0.08
    ovÃŃ
    -0.08
    zell
    -0.08
     billig
    -0.08
    íĥĿ
    -0.08
    /******/
    -0.07
    à¸ļรร
    -0.07
    ãĥģãĥ¥
    -0.07
    TRL
    -0.07
    POSITIVE LOGITS
    unto
    0.05
    osti
    0.05
    illa
    0.05
    anke
    0.05
    Ļ
    0.05
    odore
    0.05
    222
    0.05
    ég
    0.05
    akh
    0.05
    igh
    0.05
    Activations Density 0.093%

    No Known Activations