© 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. 87258
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and database queries

    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
    ABCDE
    -0.08
    ãİ
    -0.08
    æķ·
    -0.07
    overe
    -0.07
    Mex
    -0.07
    rani
    -0.07
    禮
    -0.07
    æ¨Ļ
    -0.07
    .SaveChanges
    -0.07
    è¨
    -0.07
    POSITIVE LOGITS
     search
    0.08
     filter
    0.07
     filters
    0.07
     Criterion
    0.07
    search
    0.07
     neg
    0.07
     criteria
    0.07
     criterion
    0.06
    Criteria
    0.06
     Search
    0.06
    Activations Density 0.045%

    No Known Activations