© 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. 80550
    Prev
    Next
    INDEX
    Explanations

    mentions of specific roles and positions within organizations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ç£
    -0.07
     Mig
    -0.06
    rist
    -0.06
    าà¸ĺ
    -0.06
    761
    -0.06
     appoint
    -0.06
    fern
    -0.06
    SPARENT
    -0.06
    è´¹
    -0.06
    abee
    -0.06
    POSITIVE LOGITS
     duties
    0.08
    .daily
    0.07
     Dut
    0.07
    主è¦ģ
    0.07
     primarily
    0.07
     responsibilities
    0.06
    ãĥĭãĥĥãĤ¯
    0.06
    (éĩij
    0.06
    éĩįçĤ¹
    0.06
    _contrib
    0.06
    Activations Density 0.038%

    No Known Activations