© 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. 15-LLAMASCOPE-RES-131K
    11. 27659
    Prev
    Next
    INDEX
    Explanations

    percentage values and their associations with various topics

    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
    ↵↵
    -0.10
    uitka
    -0.08
     erotische
    -0.07
    êu
    -0.07
    -0.07
    enerate
    -0.07
    EndInit
    -0.07
    eren
    -0.07
    Ñİ
    -0.07
    mium
    -0.07
    POSITIVE LOGITS
    atel
    0.07
    iá»ģn
    0.06
    oliday
    0.06
     ï
    0.06
    olland
    0.06
    .cg
    0.05
    owers
    0.05
     Funny
    0.05
    ittel
    0.05
    steder
    0.05
    Activations Density 0.010%

    No Known Activations