© 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. 92565
    Prev
    Next
    INDEX
    Explanations

    references to agricultural crops and their cultivation

    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
    s
    -0.07
    bove
    -0.06
    itis
    -0.06
    ly
    -0.06
    h
    -0.06
    erin
    -0.06
    liness
    -0.06
    prises
    -0.06
    er
    -0.06
     Venez
    -0.06
    POSITIVE LOGITS
    achuset
    0.08
    urge
    0.08
    spa
    0.07
    ulence
    0.07
    spell
    0.07
     æ¥Ń
    0.07
    aroo
    0.07
    oreal
    0.07
    aniel
    0.07
    olec
    0.07
    Activations Density 0.005%

    No Known Activations