© 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. 121455
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical suffering and conflict

    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
     flushed
    -0.07
    quette
    -0.07
    Flush
    -0.07
    ãĤ±ãĥĥãĥĪ
    -0.07
     flush
    -0.07
    flush
    -0.07
     baģlantılar
    -0.06
    ãĢĤãĢĤ↵↵
    -0.06
    715
    -0.06
    uhan
    -0.06
    POSITIVE LOGITS
    ahan
    0.07
    GT
    0.06
    ãĥįãĥ«
    0.06
    elier
    0.06
    osal
    0.06
    lain
    0.06
     Indies
    0.06
    jur
    0.06
     Picks
    0.06
    缤
    0.06
    Activations Density 0.013%

    No Known Activations