© 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 EvalsExportsinterp-engineNEWAPI 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. 93262
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and technological terms

    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
    .scalablytyped
    -0.07
    кÑģ
    -0.07
    antino
    -0.07
    же
    -0.07
    خرÙī
    -0.06
    ίκ
    -0.06
    ิว
    -0.06
    ावन
    -0.06
    istrator
    -0.06
    Äįek
    -0.06
    POSITIVE LOGITS
     two
    0.17
    两个
    0.16
    two
    0.16
     beiden
    0.15
     both
    0.14
    both
    0.13
    两
    0.12
     duo
    0.12
    åħ©
    0.12
     TWO
    0.12
    Activations Density 0.003%

    No Known Activations