© 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. 77259
    Prev
    Next
    INDEX
    Explanations

    information related to studying and scholarship opportunities abroad

    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
    jian
    -0.07
    iena
    -0.07
     SPDX
    -0.06
    olla
    -0.06
    569
    -0.06
    æŀĿ
    -0.06
     excit
    -0.06
    omp
    -0.06
    èĩªæ²»
    -0.06
    ahn
    -0.06
    POSITIVE LOGITS
    бÑĢа
    0.08
    -country
    0.07
    vä
    0.07
    undle
    0.07
    och
    0.07
    ingle
    0.06
    oking
    0.06
    ode
    0.06
    PIO
    0.06
    jom
    0.06
    Activations Density 0.001%

    No Known Activations