© 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. 125760
    Prev
    Next
    INDEX
    Explanations

    elements of structured data or arrays in programming context

    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
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.07
     Britt
    -0.07
    dit
    -0.06
    âĢº
    -0.06
    ipt
    -0.06
    roit
    -0.06
    /ubuntu
    -0.06
    ãĥĹãĥ©
    -0.06
    Idle
    -0.06
    ipher
    -0.06
    POSITIVE LOGITS
    iversit
    0.07
    -FIRST
    0.06
    agli
    0.06
    imbus
    0.06
    antro
    0.06
    sar
    0.06
    akis
    0.06
    ķ
    0.06
    ¯u
    0.06
    aley
    0.06
    Activations Density 0.029%

    No Known Activations