© 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. 129312
    Prev
    Next
    INDEX
    Explanations

    elements related to project management and configuration

    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
    assium
    -0.07
    heim
    -0.07
    dsn
    -0.06
    tracted
    -0.06
    ooky
    -0.06
    eria
    -0.06
    éŀ
    -0.06
    пеÑĢ
    -0.06
    ords
    -0.06
    viron
    -0.06
    POSITIVE LOGITS
    iana
    0.06
    ijn
    0.06
    аÑĤков
    0.06
    ä¸ģ缮
    0.06
    713
    0.06
    828
    0.06
     cocci
    0.06
    orz
    0.06
    t
    0.06
     tung
    0.06
    Activations Density 0.000%

    No Known Activations