© 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. 57780
    Prev
    Next
    INDEX
    Explanations

    mentions of official web pages or related URLs

    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
    à¤¿à¤ľ
    -0.07
    oxic
    -0.06
    ditor
    -0.06
    ustom
    -0.06
    celik
    -0.06
    olk
    -0.06
     أج
    -0.06
    omat
    -0.06
    uales
    -0.06
    amus
    -0.06
    POSITIVE LOGITS
    kud
    0.07
     official
    0.07
    ubu
    0.07
     oficial
    0.06
    ¹
    0.06
     swo
    0.06
    official
    0.06
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.06
    elsen
    0.06
     Wayback
    0.06
    Activations Density 0.002%

    No Known Activations