© 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. 79298
    Prev
    Next
    INDEX
    Explanations

    words related to creation or production processes

    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
    "struct
    -0.06
    .br
    -0.06
    inkel
    -0.06
    -variable
    -0.06
    variable
    -0.06
    lessly
    -0.06
    760
    -0.05
     duly
    -0.05
    illian
    -0.05
     variable
    -0.05
    POSITIVE LOGITS
    iad
    0.08
    MethodImpl
    0.07
    obia
    0.07
    eted
    0.07
    ersed
    0.07
    ä¸įäºĨ
    0.06
    oulder
    0.06
    uster
    0.06
     именно
    0.06
    entities
    0.06
    Activations Density 0.044%

    No Known Activations