© 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. 15-LLAMASCOPE-RES-131K
    11. 62001
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly those that indicate method declarations and access modifiers

    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
    PointerType
    -0.06
    abel
    -0.06
    puted
    -0.06
    nie
    -0.06
    MU
    -0.06
    иÑĤелÑĮной
    -0.06
    online
    -0.06
    Ä
    -0.06
    lac
    -0.06
    pane
    -0.06
    POSITIVE LOGITS
     ToString
    0.08
     toString
    0.07
    _SAN
    0.07
    .identity
    0.06
     ><?
    0.06
     identity
    0.06
    شاÙĨ
    0.06
    à¸ģารà¹Ģล
    0.06
    νο
    0.06
    æ£ļ
    0.06
    Activations Density 0.001%

    No Known Activations