© 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. 125437
    Prev
    Next
    INDEX
    Explanations

    numerical values or indicators likely related to dates, statistics, or quantities

    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
    zier
    -0.07
    ecd
    -0.06
     quilt
    -0.06
    OUN
    -0.06
    isch
    -0.06
    áj
    -0.06
    esseract
    -0.06
    ange
    -0.06
    ird
    -0.06
    ago
    -0.06
    POSITIVE LOGITS
    .AnchorStyles
    0.09
    .SizeType
    0.09
    .GraphicsUnit
    0.08
    .DockStyle
    0.08
    TRGL
    0.07
    HeaderCode
    0.07
    .ImageLayout
    0.07
    .Cursors
    0.07
    GenerationStrategy
    0.07
    ForMember
    0.07
    Activations Density 0.047%

    No Known Activations