© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103432
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and teamwork

    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
     Feinstein
    -0.07
    859
    -0.07
     fork
    -0.07
    coe
    -0.07
    olio
    -0.06
    iov
    -0.06
    fork
    -0.06
    pton
    -0.06
    shal
    -0.06
    modele
    -0.06
    POSITIVE LOGITS
    .shtml
    0.07
    ewis
    0.06
    irts
    0.06
    ä¾
    0.06
    è¢
    0.06
     Tomb
    0.06
     Ãĸz
    0.06
    çŁ
    0.06
    庫
    0.06
     Coach
    0.06
    Activations Density 0.002%

    No Known Activations