© 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. 105446
    Prev
    Next
    INDEX
    Explanations

    commands related to purchasing or acquiring products

    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
    anz
    -0.07
     lu
    -0.06
     Revel
    -0.06
     k
    -0.05
     house
    -0.05
     Lawn
    -0.05
    rani
    -0.05
     K
    -0.05
     fresh
    -0.05
    i
    -0.05
    POSITIVE LOGITS
    uristic
    0.08
    ApplicationBuilder
    0.07
     meis
    0.07
     fitte
    0.07
    ndl
    0.07
    TOTYPE
    0.07
    itecture
    0.07
    adol
    0.07
     ActionTypes
    0.07
    feld
    0.07
    Activations Density 0.000%

    No Known Activations