© 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. 86130
    Prev
    Next
    INDEX
    Explanations

    statements of belief or opinion

    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
    PIC
    -0.07
    缣
    -0.07
    orro
    -0.07
    é½
    -0.07
    GLOBALS
    -0.07
    ITCH
    -0.07
     kontakt
    -0.07
    estival
    -0.07
    bellion
    -0.07
    ä¸ģ
    -0.06
    POSITIVE LOGITS
    360
    0.06
    578
    0.06
     minority
    0.06
    ably
    0.06
    738
    0.06
     Minority
    0.06
     Minor
    0.06
    454
    0.06
    ically
    0.06
    orte
    0.06
    Activations Density 0.005%

    No Known Activations