© 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. 61393
    Prev
    Next
    INDEX
    Explanations

    numerical data related to counts and statistics

    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
    ;element
    -0.06
    indo
    -0.06
    aldo
    -0.06
    .respond
    -0.06
    alysis
    -0.06
    оÑģÑĤÑĥп
    -0.06
     sclerosis
    -0.06
    uento
    -0.06
    kus
    -0.06
     Fors
    -0.06
    POSITIVE LOGITS
    ruba
    0.07
    ythe
    0.07
    nette
    0.07
    .Automation
    0.07
    iveau
    0.07
     Gir
    0.06
    .activation
    0.06
    erman
    0.06
    ingen
    0.06
    ramework
    0.06
    Activations Density 0.042%

    No Known Activations