© 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. 74499
    Prev
    Next
    INDEX
    Explanations

    references to academic articles and their corresponding DOIs

    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
     Avery
    -0.08
    202
    -0.07
    HOOK
    -0.06
    Û²Û°Û²
    -0.06
    sem
    -0.06
    abd
    -0.06
    eward
    -0.06
    iec
    -0.06
    orum
    -0.06
    ä¿®
    -0.06
    POSITIVE LOGITS
    timeofday
    0.07
     dens
    0.06
    Å¡ak
    0.06
    Authorities
    0.06
    ожд
    0.06
     classics
    0.06
    turnstile
    0.06
    sembler
    0.06
    à¥Ĥब
    0.06
    اÙħØ©
    0.06
    Activations Density 0.006%

    No Known Activations