© 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. 9-LLAMASCOPE-RES-131K
    11. 95509
    Prev
    Next
    INDEX
    Explanations

    references to Apple products and related programming concepts

    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
    iese
    -0.07
    ADATA
    -0.07
    ovice
    -0.06
    ầm
    -0.06
    uden
    -0.06
    äll
    -0.06
    ateria
    -0.06
    ellite
    -0.06
    kaar
    -0.06
    789
    -0.06
    POSITIVE LOGITS
    finder
    0.07
    AdapterFactory
    0.07
    ystore
    0.07
    Finder
    0.07
    omba
    0.07
    locator
    0.06
    ziej
    0.06
    CF
    0.06
     XCTAssert
    0.06
     Seymour
    0.06
    Activations Density 0.074%

    No Known Activations