© 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. 62801
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic applications and qualifications

    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
     konkrét
    -0.07
    zie
    -0.07
    ̣
    -0.07
    olle
    -0.07
    ÃŃda
    -0.07
    ói
    -0.06
    celik
    -0.06
    .Navigator
    -0.06
    eldom
    -0.06
    bih
    -0.06
    POSITIVE LOGITS
     brightest
    0.07
     candidates
    0.07
     def
    0.06
    ırak
    0.06
     interested
    0.06
     outstanding
    0.06
    -interest
    0.06
    º
    0.06
     ambitious
    0.06
     som
    0.06
    Activations Density 0.023%

    No Known Activations