© 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. 82475
    Prev
    Next
    INDEX
    Explanations

    numerical or address-related information

    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
    away
    -0.07
    udge
    -0.06
    .Hosting
    -0.06
    ÙĦØŃ
    -0.06
    ue
    -0.06
    HP
    -0.06
    923
    -0.06
     Animalia
    -0.06
    mun
    -0.06
    493
    -0.06
    POSITIVE LOGITS
     offices
    0.11
     office
    0.09
    Suite
    0.08
     Offices
    0.07
     Suite
    0.07
    office
    0.07
    hq
    0.07
    åĬŀåħ¬
    0.07
     META
    0.07
     Piper
    0.07
    Activations Density 0.024%

    No Known Activations