© 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. 124751
    Prev
    Next
    INDEX
    Explanations

    instructions related to cleaning and preparing surfaces

    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
     basically
    -0.06
    ãĥ³ãĥIJ
    -0.06
     duke
    -0.06
    oen
    -0.06
    iska
    -0.06
    isches
    -0.05
     tons
    -0.05
     Cooling
    -0.05
    amina
    -0.05
    lain
    -0.05
    POSITIVE LOGITS
    peare
    0.07
    taire
    0.07
    ationToken
    0.07
    adoo
    0.07
    please
    0.07
    _ADAPTER
    0.07
    emer
    0.07
    رÙĬØ·
    0.07
    ived
    0.07
    apon
    0.07
    Activations Density 0.029%

    No Known Activations