© 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. 80435
    Prev
    Next
    INDEX
    Explanations

    contrasts between desires and practical realities

    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
    fty
    -0.08
    erd
    -0.07
    ãĤ¡
    -0.07
    vais
    -0.07
    iage
    -0.07
    FINITY
    -0.07
    мага
    -0.06
    APH
    -0.06
    etik
    -0.06
    .Îł
    -0.06
    POSITIVE LOGITS
     what
    0.10
     how
    0.10
     those
    0.08
     quello
    0.08
     ones
    0.07
    what
    0.07
     Those
    0.07
    how
    0.07
     Ø¢ÙĨÚĨÙĩ
    0.07
     How
    0.06
    Activations Density 0.039%

    No Known Activations