© 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. 42619
    Prev
    Next
    INDEX
    Explanations

    references to mental projection or hallucination

    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
    illin
    -0.06
     McCarthy
    -0.06
    324
    -0.06
    ODO
    -0.05
     Kro
    -0.05
     everything
    -0.05
    çĶŁãģį
    -0.05
     complete
    -0.05
     largest
    -0.05
    283
    -0.05
    POSITIVE LOGITS
    ıf
    0.08
    بط
    0.08
    æĿ
    0.08
    ÏĥÏĦά
    0.07
    новид
    0.07
    æ®Ĭ
    0.07
    âĺĨ
    0.07
    oner
    0.07
    TERS
    0.07
     VÅ¡ech
    0.07
    Activations Density 0.000%

    No Known Activations