© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117108
    Prev
    Next
    INDEX
    Explanations

    expressions related to leadership and notable achievements

    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
    owitz
    -0.08
    rej
    -0.07
    pra
    -0.06
    ês
    -0.06
    raison
    -0.06
    rij
    -0.06
    ä¿
    -0.06
    è°ĭ
    -0.06
    j
    -0.06
    rika
    -0.05
    POSITIVE LOGITS
     plunge
    0.09
     initiative
    0.08
     advantage
    0.07
    åĪĢ
    0.07
    gro
    0.07
     opportunity
    0.07
     Initiative
    0.06
     sóng
    0.06
    UBLE
    0.06
     jspb
    0.06
    Activations Density 0.012%

    No Known Activations