© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40400
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and technical elements

    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
    SKI
    -0.06
    ayi
    -0.06
    eder
    -0.06
    cco
    -0.06
     sadd
    -0.06
     Arrow
    -0.05
     (
    -0.05
    ++↵
    -0.05
    insk
    -0.05
     sentiment
    -0.05
    POSITIVE LOGITS
    avr
    0.08
    ervals
    0.08
    unes
    0.07
    eon
    0.07
    ompiler
    0.07
    물ìĿĦ
    0.07
    Unnamed
    0.07
    еÑĤелÑĮ
    0.07
    обÑĭ
    0.07
    ignored
    0.07
    Activations Density 0.001%

    No Known Activations