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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129669
    Prev
    Next
    INDEX
    Explanations

    terms related to academic programs and specific fields of study

    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
    imen
    -0.07
     Killer
    -0.07
    aylight
    -0.06
    Rs
    -0.06
    azen
    -0.06
    ivamente
    -0.06
    lesi
    -0.06
    appoint
    -0.06
    jen
    -0.06
    inh
    -0.06
    POSITIVE LOGITS
     Studies
    0.08
     studies
    0.07
     yönetimi
    0.06
    .addField
    0.06
     Management
    0.06
     sequence
    0.06
     management
    0.06
     cr
    0.06
     magna
    0.06
    ÑĤеÑĢн
    0.06
    Activations Density 0.048%

    No Known Activations