© 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. 118533
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of data attributes and configurations

    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
    494
    -0.07
    çĶļ
    -0.07
    556
    -0.07
    993
    -0.07
    cri
    -0.07
    uv
    -0.06
    823
    -0.06
    616
    -0.06
    493
    -0.06
    849
    -0.06
    POSITIVE LOGITS
     containing
    0.08
    onec
    0.08
    contains
    0.08
     contains
    0.07
     information
    0.07
     Contains
    0.07
    Contains
    0.07
     JADX
    0.07
     ÙħعÙĦÙĪÙħات
    0.07
     instructions
    0.07
    Activations Density 0.039%

    No Known Activations