© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38225
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to agriculture and the harvesting process

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ÑĢÑĥн
    -0.07
    /goto
    -0.07
    richt
    -0.07
     reclaimed
    -0.07
    zel
    -0.07
    jar
    -0.07
    ASN
    -0.07
    emploi
    -0.06
    oldt
    -0.06
    usz
    -0.06
    POSITIVE LOGITS
     branches
    0.08
     Branch
    0.08
     branch
    0.07
    Branch
    0.07
     fruits
    0.07
     fruit
    0.07
     Fruit
    0.06
    branches
    0.06
    _branch
    0.06
    åĸľ
    0.06
    Activations Density 0.004%

    No Known Activations