© 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. 54472
    Prev
    Next
    INDEX
    Explanations

    elements related to historical and cultural significance

    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
    Aspect
    -0.07
    eba
    -0.07
    illard
    -0.07
    ]={↵
    -0.07
    ayi
    -0.07
    lero
    -0.07
    icher
    -0.07
     newObj
    -0.06
    IBE
    -0.06
     thôi
    -0.06
    POSITIVE LOGITS
    herited
    0.08
    thanks
    0.07
    ocl
    0.07
     thanks
    0.07
     both
    0.07
     compared
    0.07
     både
    0.06
    lama
    0.06
     throughout
    0.06
    _ASM
    0.06
    Activations Density 0.024%

    No Known Activations