© 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. 17-LLAMASCOPE-RES-131K
    11. 126416
    Prev
    Next
    INDEX
    Explanations

    identifiers or references to academic articles or studies

    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
    oteca
    -0.06
    sis
    -0.06
    aga
    -0.06
     McCorm
    -0.06
     McCoy
    -0.06
    achi
    -0.06
    isle
    -0.06
    hen
    -0.05
    ër
    -0.05
    ziej
    -0.05
    POSITIVE LOGITS
    tach
    0.07
    orda
    0.07
    ãĤ¢ãĥ¼
    0.07
     tuto
    0.07
    jian
    0.07
    esson
    0.06
    IDD
    0.06
    íĦ
    0.06
    kla
    0.06
    ë¡
    0.06
    Activations Density 0.001%

    No Known Activations