© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95589
    Prev
    Next
    INDEX
    Explanations

    data structures and array assignments in code

    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
    CUS
    -0.07
    /libs
    -0.07
    êu
    -0.07
    ÑģÑĤÑİ
    -0.07
    ifar
    -0.06
    ixer
    -0.06
     isim
    -0.06
    anium
    -0.06
    ÑĪел
    -0.06
    shaw
    -0.06
    POSITIVE LOGITS
    ocha
    0.07
    ä¸Ī
    0.06
    readcr
    0.06
    ool
    0.06
    hic
    0.06
    umas
    0.06
    grav
    0.06
    lere
    0.06
     gross
    0.05
    ÏĢή
    0.05
    Activations Density 0.001%

    No Known Activations