© 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. 17-LLAMASCOPE-RES-131K
    6. 83851
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and support initiatives

    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
    bserv
    -0.08
    acci
    -0.07
    ucht
    -0.07
    ãĤĬãģ¨
    -0.07
    stial
    -0.07
    estre
    -0.07
    ufen
    -0.07
    ternet
    -0.07
    ARSER
    -0.07
    idor
    -0.07
    POSITIVE LOGITS
    rang
    0.07
    ÃĹ
    0.07
    ÃĹ↵↵
    0.06
    215
    0.06
     ÃĹ
    0.06
    aria
    0.06
    egade
    0.06
     yourself
    0.05
     sund
    0.05
     Ere
    0.05
    Activations Density 0.009%

    No Known Activations