© 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. 126048
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and structures

    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
     performance
    -0.06
     whilst
    -0.06
     credit
    -0.06
    697
    -0.06
    while
    -0.06
    plet
    -0.06
    ham
    -0.05
     while
    -0.05
    595
    -0.05
     bear
    -0.05
    POSITIVE LOGITS
     Ãĸr
    0.07
    ousse
    0.07
    داشت
    0.07
     Malk
    0.07
    Clickable
    0.06
     WCHAR
    0.06
    è¡
    0.06
    HCI
    0.06
    ãģĬ
    0.06
    üç
    0.06
    Activations Density 0.013%

    No Known Activations