© 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. 9-LLAMASCOPE-RES-131K
    11. 94667
    Prev
    Next
    INDEX
    Explanations

    structural elements and connective phrases in academic writing

    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
    ród
    -0.09
    اÙĩر
    -0.07
    *out
    -0.07
     ç©
    -0.07
     Matth
    -0.07
    ieg
    -0.07
    .DataVisualization
    -0.07
    canf
    -0.07
    actionDate
    -0.07
    κοÏį
    -0.07
    POSITIVE LOGITS
    ASON
    0.07
    –
    0.06
    –and
    0.06
     –
    0.06
    mtree
    0.06
    Tank
    0.06
     cent
    0.06
    selling
    0.06
     ded
    0.06
    0.05
    Activations Density 0.002%

    No Known Activations